2026-04-15

Added

The Rules tab now supports sorting by rule ID.
Optimization tables now offer a 'Restricting Rules' filter, allowing you to easily find products affected by specific rules.

Changed

Rerunning successful pipelines is now possible.

2026-04-14

Fixed

Improved pipeline status messages to show the correct start time.

2026-04-09

Fixed

Improved security when retrieving instance events.

2026-04-08

Fixed

Minor tweaks and enhancements made.

2026-04-01

Changed

Standardized percentage KPI granularity across the application to include decimal values.

Fixed

Corrected alignment between "Why this price" price points and the corresponding price plot.
Fixed a bug where loading spinners did not update despite completed optimization/upload.

2026-03-26

Fixed

Resolves an intermittent problem with the scope count not updating.

2026-03-25

Added

Error messages are now more readable.

Fixed

An issue preventing rule errors from appearing during optimization creation has been resolved.
Helpdesk tickets now load reliably after a fix to subscriber email validation.

2026-03-24

Fixed

Helpdesk tickets now load reliably after a fix to subscriber email validation.

2026-03-18

Fixed

Fixed a visualization error for complex rules in the "Why this price price" view.

2026-03-12

Changed

Group management transitions to the Single-Sign-On service.

2026-03-11

Added

To ensure logical pricing across bundles and product groups, we now highlight optimizations where the scopes split product groups. If you see the [?] icon as status in your Optimizations Overview, some products within the groups in your optimization are currently missing from your scope.

Changed

Help Desk comments and status histories are now displayed in chronological order, with the oldest entry at the top.
The 'Targets' column in the optimizations overview has been renamed to 'Scopes' to better reflect the primary data shown. Targets per scope remain visible on-hover.

Fixed

Resolves an issue where product images were not shown in the dashboard.
Missing rules associated with pinned optimizations have been addressed.

2026-03-04

Added

Help desk email notifications now include the full content of the most recent comment.

2026-02-25

Fixed

Copying or editing scopes no longer unintentionally changes the original scope's description.
Resolves an issue where optimizations could time out if multiple were running simultaneously.

2026-02-19

Added

Introduced the ability to schedule a one-time upload without repetition.
Rule explanation in optimization dashboard now also displays rule group impact on pricing decision.
The optimization dashboard now displays summary KPIs with greater precision on hover.

Changed

The same KPI configuration is applied for both the preview and the compare plots.

Fixed

An issue preventing optimization comparisons from loading has been resolved.

2026-02-16

Fixed

Fix missing deployment location in cloud scheduler

2026-02-16

Added

Support deployment in US region

2026-02-13

Fixed

An issue preventing optimization comparisons from loading has been resolved.

2026-02-11

Fixed

The compare table's date picker now correctly uses the chosen day instead of shifting to the previous one.

2026-02-04

Changed

The application's loading process was optimized.

2026-01-28

Added

Users can now filter for unset (missing) values within scope definitions and the optimization dashboard.

Changed

Multiselect input is now used for Boolean filter values, replacing the checkbox option.

Fixed

Fixed imprecisions in optimization preview in cases when difference between solutions was extremely small.

2026-01-22

Added

You can now filter help desk tickets to find what you need faster.
Notification for clients has been extended to include ticket creation.

Changed

Performance is enhanced as events for each instance are now loaded on demand when opening a timeline.
We’ve clarified the rule table by renaming "Definitions" to "Purpose." Hover over the items to see examples on hover.

2026-01-14

Added

Enable closing the survey after optimization creation.

Changed

The uploads page is now called Overview.
To ensure consistency with the Profit Margin, the aggregated Raw Profit Margin shown in the Optimization Preview and Comparison is now calculated based on predicted sales after returns.

2026-01-12

Changed

Allow S3 bucket owners to have full control over uploaded objects in the bucket.

2026-01-07

Fixed

Resolved the problem where rules could not be created using a 0.0 value.

2026-01-07

Changed

The value field is now displayed only when the selected rule template requires it.
Better explain why rerun pipeline button is disabled.

Fixed

Users can now rerun pipelines when issues are client-side related.
Filtering for a non-existent item in optimization dashboard now correctly returns an empty result.

2025-12-29

Added

A new metric was added to upload timeline, illustrating the impact of Liquidation End Profit.

Changed

Selecting a group now refreshes the page.
The Landing page after login has been updated to the uploads page.
Percentage labels were updated to clearly distinguish between percentage point (pp) changes and relative percentage growth.

Fixed

Resolved an issue in optimization dashboard where product rule explanations included irrelevant rules under specific conditions.
Resolves an issue where numerical filters failed to operate correctly when the 'not equal' operator was applied.

2025-12-19

Fixed

Resolves an issue where numerical filters failed to operate correctly when the 'not equal' operator was applied.

2025-12-17

Added

Added support for file attachments in the Help Desk section.

Fixed

Improves the experience by having expanded ticket rows maintain their position within the user's current sort and pagination view.
Fixed formatting of small fractions in upload timeline.

2025-12-11

Fixed

Resolved an issue where the optimization dashboard sometimes failed to load when navigating to it directly through a link.
Resolves a problem that could cause the scope count update process to fail unexpectedly.

2025-12-03

Added

Improved the timeline dashboard on the Uploads page by adding Revenue as a selectable Y-axis option.
Dates have been integrated into the profit curves located within the explain tab.

Changed

Optimization Group Profits are now utilized to explain price and marketing changes. For instance, when all sizes of a product must have the same price, the explain curve shows the combined profit for all sizes instead of individual profits for each size.
New Feature: You can now send data to multiple channels at once using efficient batches. New filtering options have been added to the frontend to help you manage these selections easily.
System Update: We have updated the data transport system. Grouped CSV exports now use a long format data structure (replacing the old wide format).

⚠️ Important Note: Due to the switch to long format, grouped CSV exports are no longer compatible with existing Tradebyte pandas workflows. Please verify your data scripts and update them to handle the new format.

2025-11-28

Fixed

Resolved a minor issue affecting Snowflake uploads.

2025-11-26

Changed

The Snowflake upload feature now accommodates larger tables through its bulk upload capabilities.

2025-11-24

Added

Tradebyte upload now supports uploading larger optimizations via streaming uploads

2025-11-21

Fixed

Resolves an issue where project configurations could fail to update.

2025-11-19

Changed

The pipeline rerun interface now shows a disabled rerun button where it was previously absent.

Fixed

Resolves an issue where direct links to app pages (e.g link from emails) failed to open correctly if you had to log in first.

2025-11-12

Added

Additional KPIs are now available on hover for current prices point in the optimization preview.

Changed

The Timeline Monitoring section of the Uploads page now displays actual Sales Before Returns only for the products in the most recent forecast instead of all products before.'.

Fixed

Fixed optimization dashboard histogram not showing full range of X-axis ticks in some cases.
Small improvements for filtering in compare table.
Addresses an issue where optimization creation failed for scopes that contained datetime constraints.

2025-11-05

Fixed

Fixed failing scheduled uploads due to an issue with email notifications

2025-11-05

Added

Subscribers now receive email notifications for new comments on tickets.

Changed

The filtering in the comparison table now has a consistent look and feel with the scope form.
The Price and Marketing section columns are now reordered and renamed, showing always "Current Price", "Optimal Price" and "Explain" columns to assist first-time users.

Deprecated

Target Sales rules and KPIs have been removed from the front-end, as rules can now directly reference Liquidation End STR values, such as 'Liquidation End STR ≥ 80%'.

Fixed

Resolved an issue in histograms where values were mistakenly presented as NaN or zero instead of 'M'.

2025-10-29

Added

Predicted Marketing Cost is now avaliable as a KPI in the preview curve

2025-10-23

Fixed

A precision issue in floating point rounding that caused incorrect 'out of bounds' messages for profit weight during optimization has been corrected.

2025-10-22

Added

Users can now manually retry a failed pipeline run. If a pipeline has failed due to missing data or requires customer action, a rerun can be triggered from the pipeline status bar after the issue has been addressed.

2025-10-15

Added

Help desk tickets are now linked to the pipeline status sidebar and the changelog sidebar.

Fixed

The download of the optimization could encounter an issue.

2025-10-13

Fixed

Issues with creating, editing, and deleting upload schedules have been resolved.

2025-10-08

Added

Users can now view the full file path for their uploaded files directly within the upload timeline.

2025-10-06

Fixed

lockdown content security policy to angular

2025-10-01

Added

Commercetools Direct Price Synchronization A direct integration between 7Learnings and Commercetools is now available. This functionality enables the automatic transfer of optimized prices from 7Learnings, allowing for the immediate update of embedded prices within Commercetools without any manual intervention.

2025-09-25

Fixed

Fixed price-generating rules to prevent unintended selection of multiple marketing options in marketing optimizations.

2025-09-24

Fixed

The '(edited)' label will no longer show on comments that have just been submitted.

2025-09-17

Fixed

Resolved an issue causing incorrect color display in histograms.
Improved formatting for values shown in rule names.

2025-09-03

Fixed

Fixed "Rule depends on deleted scope" error not shown after scope was deleted.
Improved accuracy of optimization preview in case scope definitions split optimization groups.

2025-08-29

Fixed

Rework ineffective KPI from scope options.
Fixed incorrect wAvg Price Change displayed for "Do Nothing" scenario in optimization dashboard.

2025-08-28

Fixed

Improved app stability and overall experience.

2025-08-27

Added

Choose which KPIs to display on the summary graph in the compare table.

Changed

Remove an ineffective KPI from the available scope options.

2025-08-21

Fixed

Resolved the problem with creating rule comments.

2025-08-20

Fixed

Resolved the problem where no optimizations could be created.

2025-08-20

Changed

Redesigned the login interface for a more modern and intuitive experience.

2025-08-14

Fixed

Fix updating scope might lead 500 error.

2025-08-13

Added

It is now possible to group multiple rules together and rename these, making it significantly easier to create and manage complex optimizations involving numerous rules or scopes.
- Group Rules: Combine multiple rules into a single, manageable group to keep your workspace organized.
- Custom Naming: Rename rule groups for better clarity and quick identification of their purpose.
- Simplified Setup: Streamline the configuration of large-scale optimizations that span many rules or scopes.

Changed

Hovering over a rule template, now shows its full description.

2025-08-12

Fixed

Minor tweaks and enhancements made.

2025-08-11

Changed

Improved the precision of your upload details.

2025-08-08

Fixed

Shopify bulk operations now accurately report status without misleading error messages.

2025-08-07

Added

Enhanced readability for quoted content within help desk ticket comments.

Changed

Login Interface got resdesigned.
Filters now consistently apply across all columns on every page.

2025-08-05

Fixed

Fix upload integration might fail with timezone casting error.
Fix downloading optimization might fail with snapshot optimizations_comparison view error.

2025-07-31

Fixed

Fix downloading newly added download format might fail.

2025-07-30

Fixed

Minor tweaks and enhancements made.

2025-07-23

Added

Timeline comments are now editable for every entity.
"STR at Liquidation End" KPI is now available in optimization preview.
Add a help ticket template to enhance description quality.
You can now see the predicted Liquidation End Profit on the preview curve when setting your targets. To configure the preview curve KPIs, please use the settings button below the curve.

Fixed

Ensured all help desk data is now fully visible and easy to read.
Expand and collapse rows to view more details about failed optimizations.

2025-07-16

Added

Enable comment editing in help desk section.
Hovering over chips in Explain Rule, now displays expanded information about rule status, including failure, out-of-scope, or single price selection reasons.

Fixed

Ensured rule chips always look right when you move them.

2025-07-02

Changed

Increased optimizer efficiency.

2025-07-01

Fixed

Minor tweaks and enhancements made.

2025-06-30

Added

Get notified by email when your support request is answered.

2025-06-25

Fixed

Fixed Shopify upload behavior so uploads always complete in the background and you won't see incorrect error messages.

2025-06-20

Fixed

Fixed an issue that could cause uploads to get stuck.

2025-06-18

Changed

Removed redundant rule suffixes ('#n') from duplicated entries.

Fixed

Resolved: Users could encounter a 500 error when accessing the optimization dashboard.

2025-06-10

Fixed

Resolved an issue that stopped Tradebyte downloads.

2025-06-06

Fixed

Performance boost: Optimizer now supports more rules for larger optimizations.

2025-06-04

Fixed

Fixed an issue where optimization jobs might not start.

2025-05-27

Added

A Glossary section is now available in the help documentation, providing term definitions.

Fixed

Improved download stability and added a progress indicator.

2025-05-22

Changed

Set the default visible height of timeline and help desk comment fields to 7 rows.

Fixed

Fix: Upload scheduling now correctly handles Sundays.

2025-05-06

Added

Enable rule editing within optimization creation flow.
Preview curve now includes an optional Discount KPI; data scientist will need to enable it.
We added a new KPI called "KVI Rank". It's available in the Scope section, where you can create scopes for your most important products using the new KPI. By default, the ranking is based on historical revenue, the number of competitor prices and the historical product margin as KVIs are highly price-sensitive. Example: "KVI Rank < 100" will select your 100 most important products.

Changed

Improved rule explain: Expanded rule name area for better usability.

Fixed

Prevent overflow in rule explain section for failing rules.
More reliable uploads: Addressed problems with long running uploads.

2025-04-30

Added

Show rule IDs for easier rule identification.
Help Desk: Support "Question" ticket option.

Changed

Help Desk: Emphasis all links for easy navigation.

Fixed

Help Desk: Standardized bullet point list indentation.

2025-04-23

Changed

Subtle improvements and refinements applied.

2025-04-16

Added

Frontend support tickets with user comments are now live.

2025-04-09

Added

Improve the benchmark group feature in the new explain section.

Fixed

Use 'B' to represent billions on the axis label.
Resolved a problem where the optimization comparison view sometimes failed to open.
Fixed an issue that could change data types during optimization upload or download.

2025-03-28

Fixed

Resolved issue where comparison dashboard could show a 404 error.

2025-03-26

Added

We've added new optimization features and you can now directly send your optimized data to Snowflake!

Fixed

Fixed Minor issues with upload channel filter and veto functionality.

2025-03-24

Fixed

Display missing icon for benchmark groups.

2025-03-20

Fixed

Refined upload error handling for clarity.

2025-03-19

Added

Introduced a new "Explain Benchmark Group" visualization, displaying weekly sales performance against a selectable benchmark group, highlighting the current week and liquidation end date on an interactive timeline.

Changed

Sharing just got easier! URLs now automatically include your active user group.

2025-03-14

Fixed

Resolved issue where filtering with true/false was not working correctly.

2025-03-12

Changed

Minor tweaks and enhancements made.

2025-03-06

Fixed

Editing a scope should now work correctly without server errors.

2025-03-05

Changed

Feedback Dialog: Closing the feedback dialog with the Escape key will now trigger a reminder next month, rather than upon the next optimization creation.

Fixed

Deletion Rule: Resolved an issue where fixing the deletion rule could trigger a server error.

2025-02-26

Added

Made KPIs configurable in the Optimization Preview Curve.

Fixed

Fixed an issue where update scope could lead to "not found" error.
Fixed: Optimization previews now work reliably, even with complex scope definition.

2025-02-20

Fixed

Fixed an issue where update scope could lead to "not found" error.

2025-02-19

Fixed

Fix cropped dropdown in upload edit form.

2025-02-14

Fixed

Split CSV exports now correctly uses renamed column names.

2025-02-13

Added

Display recent pipeline status and the reason behind failure.
Add new widget to explain marketing decision. It contains the rules used and both profit and seaonal profit curves.

2025-02-10

Fixed

Optimization creation may fail due to invalid setup.

2025-02-06

Fixed

Resolved an issue where upload channel filtering could lead to upload failures.
Fixed an issue that could prevent optimization results from being uploaded to Google BigQuery.

2025-02-05

Added

Display the upload information on hover in upload timeline.

Changed

Keep the feedback dialog open until feedabck is submitted.

2025-02-04

Fixed

Minor tweaks and enhancements made.

2025-01-22

Added

Add new help text of Product Group.

2025-01-20

Fixed

Resolved an issue where the Gross Red Price interpolation was incorrect when duplicate price points were present in the optimizer.

2025-01-17

Fixed

Fixed an issue where creating or editing a scheduled upload would fail.

2025-01-15

Added

Introducing transparent order optimization! Our enhanced comparison table now reveals the reasoning behind each recommended order quantity. See the key factors driving these calculations and understand exactly how our system optimizes your inventory levels.

2025-01-08

Changed

The column selection functionality of optimization comparsion table has been redesigned. Enabling the selection of multiple columns at once. Additionally the new design now supports autocompletion.

Fixed

Fixed incorrect steering target dial drawn for new optimizations.

2025-01-02

Added

Add +-14 days dashboard to uploads for an overall predictions so that its easier to correctly schedule uploads.

2024-12-20

Fixed

Fixed a bug that caused errors during uploads to FTPS servers.

2024-12-19

Fixed

Allow KPI selection in the "Other" tab from the comparison table.

2024-12-18

Fixed

Minor tweaks and enhancements made.

2024-12-13

Fixed

Fix issue where upload page may stay in an infinite loading state.

2024-12-12

Added

Added explanatory text to the target section of optimization edit page for when current prices preview point is above the curve.
A new documentation section for Upload Channels is available.
Help sections (Scopes, Rules, Forecast Variants) are linked to their respective fields on the Optimizations Edit page. Clicking a label or icon (e.g., Scope) opens the multi-section help sidebar, automatically focusing on the relevant section (e.g., Scopes).
Introduced a feature to view today's forecast status.

Fixed

Fix form reset issue when re-editing scope with in-progress count evaluation.
Fixed scope target being deselected if revenue slider is dragged all the way to the left when creating optimization.

2024-11-27

Fixed

Fixed smaller number of categorical values being displayed in histogram plot when viewing more than one optimization.
Fixed some rules that were incorrectly marked as incompatible with the forecast.

2024-11-20

Fixed

Fixed smaller number of categorical values being displayed in histogram plot when viewing more than one optimization.

2024-11-18

Fixed

Fixed some rules that were incorrectly marked as incompatible with the forecast.

2024-11-14

Fixed

Address the issue where the scope name is not correctly reflected in the download filename when the scope name includes umlauts.

2024-11-06

Changed

Show help section more clearly.

Fixed

Fix issue where split CSV downloads may produce empty results.

2024-10-30

Fixed

Fix misleading formatting for sales in preview curve on hover in optimization edit page.

2024-10-25

Fixed

Fixed an issue where a price-interpolating rule could violate optimization group consistency because of a missing value.
Fixed an issue where a rule could violate optimization group consistency, if rule's scope included only subset of products in optimization group.
Fixed inconsistent optimization groups could cause missing price selections in optimization result.

2024-10-25

Added

You can now schedule uploads in specific timezones other than UTC.

2024-10-17

Fixed

Resolved an issue causing infinite page loading.

2024-10-17

Fixed

Fixed usage of main forecast variant for all optimization comparison snapshots

2024-10-17

Fixed

Resolved an issue with optimization integration ignoring the delimiter.

2024-10-16

Fixed

Fix for unstable steering app (DB connection)

2024-10-16

Changed

Minor tweaks and enhancements made.

2024-10-11

Fixed

Fixed comments are not properly displayed.

2024-10-11

Fixed

Hotfix for failing optimizations (PARSE_JSON)

2024-10-09

Added

Display the specific changes made to the scope or rule during edit events, highlighting the differences between the original and updated configurations.
Added a new collection of frequently asked questions (FAQs) from users to enhance support and resource accessibility.

2024-10-02

Added

Add new help texts of Scopes, Rules and Stock

2024-09-25

Changed

The From/Till column in Optimizations Table Overview now displays the creation date of the optimization instead. The optimization forecast range is still available via hovering over the creation date.

2024-09-18

Changed

Display profit margin for all points in optimization preview, even if Profit Margin target is not available.

2024-09-11

Added

Expanded help text to provide more comprehensive guidance, starting with target selection in optimization edit page.
A new KPI; Revenue Impact. Has been added to the upload evaluation. This KPI provides a better notion of the trade-off between profit and revenue.

Changed

Added locale-aware number formatting for revenue, profit, and sales in hover on preview curves.
Enhanced table with a sticky header to keep column titles in view.

Fixed

Marked upload configuration fields as required.

2024-08-30

Fixed

Resolved issue where scheduled uploads were not functioning correctly.

2024-08-29

Added

Added functionality to select specific markets/channels for price upload.

Fixed

Addressed issue where loading icon persisted without updating scope status or product count.

2024-08-21

Added

Display the start and end date below the optimization name in the timeline and add profit impact metric, to better evaluate upload performance.

Changed

Updated KPI names in all relevant tables and histograms to align with the defined ones.

Fixed

Fixed overestimation of current prices point when previewing optimization.
Resolve issue where scheduled uploads incorrectly display an error icon even after successful completion.

2024-08-15

Fixed

Use currency symbols based on market settings rather than relying on browser locale.

2024-08-14

Added

Re-added negative Profit Margin optimization targets.

Changed

Improved performance of optimization preview. Depending on optimization, reduced loading times by up to 40%.
Relocate rule errors to the status column for improved clarity.
Relocate scope warnings to the status column and to timeline for improved clarity.
Make the comment field required when submitting a rating for the optimization creation experience.

Fixed

Use the correct local currency for Switzerland.

2024-08-07

Changed

Minor tweaks and enhancements made.

2024-08-01

Fixed

Fixed issue with optimization preview not loading due to sampling of duplicate points on rare occasions.

2024-07-31

Changed

Set a max width for scope column and truncate long names in optimizations view to prevent blocking other KPIs.

Fixed

Fix incorrect steering dial displayed for first target of a multi-target optimization.

2024-07-25

Fixed

Resolve issue where automated upload may run multiple times.

2024-07-24

Added

Display the number of days in the date range input when creating optimizations.

Changed

Improved pop-up notifications for forecast and optimization date range applications.
Introduced the capability to display images within the changelog, enhancing visual communication of updates.
Clicking on date icon will open calendar instead of setting values to present range.
Renamed Seasonal Profit to Liquidation End Profit as this profit refers to the total profit at Liquidation End date (including write downs).

2024-07-17

Added

When creating an optimization upload, it is now possible to select multiple integration destinations for the same optimization simultaneously.

Changed

The competitor price plot was improved and prices are now easier to distinguish.
The optimization preview curve now fully extends to the left of the Maximum Margin Point until the Minimum Revenue Point.

2024-07-10

Changed

Disabled edit icon for failed uploads.
Improve Profit Weight Target by rounding to full percentage targets e.g. 24% instead of 24.1%

Fixed

Enhanced number formatting to be locale-aware for consistent decimal display.

2024-07-03

Changed

The target selection slider in the optimization preview curve, now shows the actual value while dragging. Allowing for a more precise selection of the selected target.
Price history plots layout is now more readable.

Fixed

Resolved scope filter reset issue during multi-scope edits.

2024-06-26

Fixed

Fix overlapping x-axis ticks in price history plots.

2024-06-25

Fixed

Resolve the issue of previous uploads disappearing.

2024-06-24

Fixed

Ensure scope count updates correctly.

2024-06-19

Added

Added new target type: Δ Profit / Δ Revenue, that lets you steer prices towards particular Profit-Revenue slope.

Changed

Enhanced plot clarity by adjusting legend position and default selection.

2024-06-14

Fixed

Fixed display for price history plots not being correctly sorted.

2024-06-12

Fixed

Fixed two identical rows appearing on rare occasion when creating a new upload.
Fixed 0 is not recognized as a valid value when editing scope.

2024-06-05

Changed

When copying an optimization, to avoid manual edits, the end date is now limited to the forecast end date if the copied optimization period is longer. If there is no valid forecast for today, the date range selection will be cleared.
Selection of negative Profit Margin targets is not allowed anymore. Instead, optimizations should be steered using the Profit Weight target type.
Updated feedback prompt to appear only if more than a month has passed since the previous one.
Moved the prompt to the bottom center to prevent it to obscure the timeline and enhance the overall layout.
The scheduled upload will now proceed only if there is a new forecast.

2024-05-30

Added

Implemented new page for creating and editing uploads, replacing inline edit in table.

Fixed

Display correct KPI names in scopes table.

2024-05-22

Added

Improved the upload page to display timestamps with UTC hours and minutes, providing clear time zone information for when optimizations were uploaded relative to Coordinated Universal Time.
Display Δ Profit/ Δ Revenue in preview curve hover to prepare as new target type

Changed

Changelog moved to sidebar dialog for better visibility, ensuring consistency and maximizing space.
Reversed fields order in optimization edit page for better intuitiveness: preview first, then target selection.
Enhanced optimization display during runtime to show an empty product count instead of indicating 0.

2024-04-26

Added

Added new optimization target type: Profit Weight
Display tooltip descriptions of target types in select box when creating optimization.

Changed

Filtering by price KPI's in the comparison dashboard is now easier. A clickable icon now gives access to the sidebar and restores the text-click functionality for filtering.
The search term dialog in the optimization comparison dashboard is now always centrally positioned for complete display.
Placement of cancel/submit buttons to the right of the search term dialog was adjusted, to avoid overlap with select options.

Fixed

Currency information is now more accurate and up-to-date.
Clicking on list of scopes in optimization dashboard will now search for products belonging to every scope in the list.

2024-04-19

Fixed

Resolved potential login failure for email authentication.

2024-04-17

Added

The Identifiers section of the comparison table is now customizable, enabling users to effortlessly add or remove columns based on their preferences.
The comparison dashboard can now be filtered via the scope names in the optimization. This way is possible to view products belonging to a certain scope only.

Changed

Enhanced functionality to allow editing configurations for pending uploads.
In addition to uploading an optimization immediately, now is possible to create an upload instance of the selected optimization in the upload section to be uploaded later on.

2024-04-09

Added

It's possible now to edit the name of optimizations after they have been created.

Changed

The 'Create' and 'View' buttons have been relocated to the top of the Optimization Comparison interface.

Fixed

The spinner has been fixed and is shown during the re-evaluation process.
Addressed the issue to ensure that edit events are now properly shown within the scope timeline.
Implemented a fix to enable users to empty reviewers successfully during the editing process.

2024-04-02

Fixed

Ensure that scopes undergoing evaluation are not utilized in the optimization process.

2024-03-28

Fixed

scope creation with huge filter lists

2024-03-20

Added

Users with upload permissions can now activate the auto-upload functionality by selecting the option for automated upload.

Changed

Introducing progress spinner for scopes under evaluation, streamlining initialization wait times.
Introducing multi-line functionality in the rule template dropdown, enhancing visibility for easier selection.

Fixed

Addressed the problem of predicted values not being vertically aligned in the optimizations table.

2024-03-12

Fixed

Fix issue downloading scopes for user group

2024-03-12

Added

Allow to select exact search value in forms that support it.

Fixed

Fix autocomplete input persisting only up to 100 values.

2024-03-07

Fixed

Fix scheduled upload doesn't preserve steering target

2024-03-06

Added

When creating an optimization, a target type can be chosen for the selected point in the preview graph, enabling more precise optimization goals.
A new Maximum Profit target type is introduced for preview points, allowing optimization for maximum profit potential.
Hovering over a rule in the Explain Price Decision tab of the optimization dashboard now reveals the full rule name, offering greater transparency into pricing decisions.

Changed

Copying an optimization now includes the original targets, not just the final optimization result, ensuring the initial configuration is preserved and facilitating re-running the optimization with different settings.

2024-03-01

Added

Users without upload permissions, are now able to review or/and approve/upload optimizations
Adding support for markdown comments

Fixed

Adding support for special characters in comments. e.g. apostrophes.
Fix can't edit uploads unless they are in the first page.

2024-02-28

Fixed

Fix upload to Google storage bucket might fail

2024-02-20

Fixed

Fix optimization status not detected correctly because of comments posted while optimization was still running.

2024-02-19

Added

Display price history graph for selected column on top of other graphs in optimization comparison dashboard.
Scopes, rules, optimizations, and uploads now all have sharable links to their timelines.
Automatically open timeline of newly created upload, optimization, scope, or rule.
Paginate and scroll into view if selected instance is not visible.

Fixed

Fix unable to edit in-progress upload.

2024-02-07

Changed

Make all rules available for selection when creating optimization. Highlight and display error for invalid rules.

Fixed

Fixed date range change triggered reset of targets to current prices revenue when creating optimization.
Improved precision of optimizations with respect to given profit margin targets.
Fixed incorrectly inferred types of column when editing a scope filter.
Fixed unable to create scope with timestamp filter.
Fixed histogram in optimization dashboard sometimes displaying more x-axis ticks than necessary.

2024-01-31

Changed

Redesigned upload scheduling, with a cleaner and more intuitive UI.

Fixed

Allowing selection of boolean and empty values in scope creation
Implement text truncation with ellipsis for better overflow handling in search values.

2024-01-24

Fixed

Improve response time when creating/editing a scope

2024-01-16

Added

Enabling advanced search for categorical KPIs, via OR operator.
Add option for Daily repetition of scheduled uploads.

Changed

Enabling sorting rule definitions by name.

Fixed

Unable to handle TIMESTAMP datatype while creating a scope

2024-01-09

Added

Display rule definitions in "Rules" page.
Display rule fallback when hovering over rule definition.

Changed

Allow interaction with search bar while optimization dashboard is loading.

Fixed

Remove histogram column from tabs when it is not available for the selected optimization.
Fix division by zero error in preview graph.
When creating optimization, fixed 'End Date' sometimes being updated to most recent date, overriding user input.

2024-01-05

Fixed

When creating optimization, fixed 'End Date' sometimes being updated to most recent date, overriding user input.

2023-12-28

Added

Added "Share Search Results" button in search bar of optimization dashboard.
Added search for vetoed products in optimization dashboard.

Changed

Separated Profit and Seasonal Profit plots in Explain tab of optimization dashboard.

Fixed

Fixed overflow of long comments in timeline.

2023-12-21

Fixed

fixed updating and downloading scopes

2023-12-21

Fixed

Fix upload scheduling execution

2023-12-20

Added

Display optimization accuracy metrics in timeline.
Add caching technology to the front-end to make the preview of previously optimized product scopes faster. The second optimization with the same optimization scope should now be much faster.

Changed

Enable search by failing or passing rules in optimization comparison dashboard.

2023-12-05

Changed

Enhance user profile aesthetics by implementing initials as the icon.
Add ellipses for long names, enhancing readability.

2023-11-30

Added

Support Tradebyte Pricing API. Optimizations can now be uploaded directly to TBOne system

Changed

Use up-to-date rule definitions when copying older optimizations, instead of showing an error for outdated ones.

2023-11-27

Fixed

Fix not being able to upload/download CSV integrations.

2023-11-23

Added

Introducing selection of reviewers for Pending Uploads.

Fixed

Fix rule selection not available when trying to edit selected rules in optimization dashboard's search bar.
Do not redirect to Uploads page when downloading an optimization.
Support scope filter with much bigger number of specific values.

2023-11-15

Changed

Preserve optimization date range length when copying.

Fixed

Restrict user selections to a 14-day range for optimization date range.

2023-11-07

Added

Introduce expand icon to toggle visibility of multiple targets in optimizations page.

Changed

The veto list is persistently stored when creating or approving uploads.

Fixed

Fix error message after optimization was pinned.

2023-10-27

Added

Add paginator to opimizations page to simplify the table.
Add paginator uploads page to simplify the table.

Changed

##20200 - Improved file organization by renaming internal filenames in the downloaded zip with a prefix of the zip filename, enhancing clarity and consistency. Previously, internal filenames contained only the tradebyte channel key.

Fixed

Change to corresponding group automatically after reviewing an upload.
Fix compare dashboard crashes when all rows are filtered out.

2023-10-20

Added

Enable multiple weekdays selection for weekly uploads.

Changed

Switch display from creation date to edit date for forecast's last data update in optimization creation page.
Group histogram outliers in compare dashboard.

2023-10-04

Added

Support Portuguese locale.

Changed

Enable hover info between available points in price history graph.

Fixed

Fix the link/button in mail not showing in some cases.

2023-09-28

Fixed

false positive rule incompatibility error
Fix a problem with an empty row sometimes appearing after creating a scheduled upload.

2023-09-21

Added

Show date of last update for selected forecast when creating optimization.
Display errors if rules are not compatible with the selected forecast in optimization creation.
Schedule a weekly price update in upload page.
Enable deletion for pending uploads.

Changed

Display status icon for pending uploads.
Sort kpis columns alphabetically in compare table.

Fixed

Highlight empty value fields when submitting a Scope.
Display time in upload table in user local timezone.

2023-09-12

Added

Support interpolating rule prices from product attributes
Support Danish locale

Fixed

Fix approve/upload in upload page.

2023-08-29

Fixed

Fix welcome message shown on every page reload.

2023-08-25

Changed

Updated to Angular 14.

Fixed

Speed up creation of scopes based on attributes with large number of unique values. Values for such attributes will no longer be validated.
Greet user once for the same session.

2023-08-08

Fixed

Fix overlapping prices on Y-axis in price history view of optimization comparison table.

2023-07-27

Added

More competitor price graphs are now available in price history panel of optimization comparison table.

Fixed

Fixed missing competitor prices in rule explanation panel of optimization comparison table.

2023-07-22

Fixed

Fix unable to download the optimization.

2023-07-20

Added

Enable switching optimizations of uploads

Fixed

Fix parsing of numerical values when editing search terms in optimizations compare table for some locales.
Update the upload page instantly after adding an upload.
Handle over-sized product filters

2023-07-17

Added

Display the destination of the upload.
Examples of products are now available when hovering over a detected scope intersection while creating an optimization.

Changed

Improve login screen layout.

2023-07-05

Added

Add ability to comment when reviewing an upload.

Fixed

Fixed backend error on change of filter operator when creating a scope.
Missing values will now be considered false in boolean scope filters.

2023-06-28

Added

New uploads will now include "Content" column.
If available, exact time of price change will now be displayed in price history view of optimization comparison table.

Fixed

Fixed upload status having incorrect icon sometimes.

2023-06-20

Added

If available, add seasonal profit graph to "Explain" column of optimization comparison table.
Added new explain tag containing number of products in optimization group. This tag lets you know if product's pricing can be influenced by other products within its optimization group.

Changed

Improved explain tags in optimization comparison table. Now they contain objective numerical values, and are color-coded according to their impact.

Fixed

Fixed search in compare table if column is missing for one of selected optimizations.

2023-06-16

Fixed

Fixed search in compare table if column is missing for one of selected optimizations.

2023-06-15

Fixed

Preserve comments indentation in timeline.

2023-06-12

Fixed

Fixed issue where optimization was not automatically uploaded after user with upload permissions clicked on the upload button.

2023-06-07

Added

Id of the selected upload is stored in the address of the tool website. This link can be shared and it will redirect to the compare table of the selected optimization.
In the upload section, users with permissions can approve/upload pending optimizations using the upload button.
Ids of the selected optimizations is stored in the address of the tool website. This link can be shared and it will redirect to the compare table of the selected optimizations.

Changed

Enable pushing optimizations to upload section for users without upload permission. Optimizations will be pending for approval in the upload section.
In the compare table, for Explain and price columns, you can now click on the item to see a separate pop-up for rules explanation and price history information.

Fixed

Individual product prices are no longer affected by overlapping scopes.

2023-05-24

Added

Detect and inform about scope overlaps when creating optimization.

2023-05-19

Added

Show price history in compare table.

2023-05-12

Added

Disable submit button when creating optimization with multiple targets for the same scope.
Enable optimization view from upload section.
Enable comments on uploads.

2023-05-02

Added

Add 'Uploads' section.

Changed

Improved accuracy of preview curve when creating optimization.

Fixed

Prevent price labels from overlapping on small ranges in rule explanation column of optimization comparison table.
Fix unable to search boolean columns in optimization comparison table.

2023-04-19

Added

Display separate allowed prices for each rule in Explain column of optimization comparison table.

Changed

Increased width of histogram search dropdown in optimization comparison.

2023-04-14

Fixed

Fix unable to create optimization when only a single preview point is available.

2023-04-12

Added

Remember and display recently used histogram KPIs in optimization comparison.
Add autocompletion when selecting histogram KPI from dropdown in optimization comparison.

Changed

Stock and Discount are no longer displayed by default in histogram of optimization comparison.

2023-04-05

Added

Notify user about new comments of other users on optimizations, rules and scopes

2023-03-28

Added

Add checkbox for search with exact matching in optimization comparison table.

Changed

Moved Elasticity KPI to Pricing section of the optimization comparison table.
Elasticity KPI definition change: Use midpoint formula only for the price change from Current Price to Optimal Price.
Competitive Positioning is now a percentage value: +10% means the Optimal Price is 10% higher than Min Competitor Price.

Removed

Removed unnecessary internal KPIs from optimization comparison table.

2023-03-22

Changed

Enabled new Google Sign In
Profit Margin is now among main KPI choices for histogram above comparison table.

Fixed

Fixed incorrect profit curves in comparison table for optimizations shorter than 2 weeks
Fixed maximum revenue target sometimes failing to be preselected when copying optimization

2023-03-15

Fixed

Fix daylight saving time might cause incorrect date range

2023-03-10

Fixed

Fix not visible products in the comparison table for some optimizations.

2023-03-09

Added

Display competitor prices in comparison table under Pricing->Explain.

Changed

Exclude internal columns from compare table download.

Fixed

Fix profit margin not shown for optimizations with one target.

2023-03-01

Changed

Improve clarity of automatically selected targets notification

Fixed

Immediately show password strength feedback in "Reset Password" form.

2023-02-23

Fixed

Fix incorrect user information in optimization status

2023-02-15

Fixed

Fix displaying newly added comments at real-time.

2023-02-10

Changed

Relevant filter columns will be included in scope download
Targets will be preselected based on margin instead of revenue when copying optimization
Move created by and edited by columns to status feed instead of the main table for scopes and rules.

Fixed

Fix display of missing dates in comparison table.

2023-02-02

Added

Autocomplete is added when searching for categorical columns in the comparison table.
Add plot of predicted profits for different product prices in Pricing->Explain column of comparison table.
In the comparison table under Pricing->Explain, display additional tags to better understand factors considered in pricing decision.

Fixed

Fix not able to edit search term without specified column.

2023-02-01

Fixed

Fix unable to add comments for rules.

2023-01-31

Fixed

Fixed preview not loading for some optimizations

2023-01-27

Added

In the optimization page, clicking on the status icon will display the history of the optimization. It is possible to collaborate by leaving comments. This feature is enabled as well for scope and rule pages by adding a new status icon to the table.

Changed

Group general filters under 'Identifiers'.
'Applied rules' and 'Failing rules' filters are moved from Pricing section to first-level menu above 'Identifiers'.
Display the name of selected item in the title of History section.
Automatic log out will occur after 15 minutes if tab is out of focus.
Preview curve now starts at maximum margin instead of minimum revenue point.

Removed

Remove 'Passing all rules' from filter menu in the comparison table.

2023-01-12

Changed

Adjust size of notification dropdown.
Make filter definitions easier to access during scope creation.

2023-01-04

Added

In the optimization comparison table, when clicking on the filter icon, there will be a new item 'Applied rules' under the Pricing section. This new filter will open a dialog with a drop-down containing all the rules names from the selected optimizations. It will show the products where that selected rule was applied. Note that the filter is enabled only for newly created optimizations.
In the optimization creation page, Main forecast will be on top of the list and followed by the forecasts with voucher spending in ascending order, if available.

2022-12-28

Fixed

The optimization comparison table keeps stable columns after filtering

2022-12-22

Fixed

In the optimization page, clicking the view button will only close the optimization comparison table.

2022-12-21

Changed

Updated to Angular 13

For improved security and a few framework bugfixes.

In the optimization page, you can hide or show an optimization in the comparison table using the new eye icon. When you click on the icon, it will also change its state (open/close).

Fixed

When hovering over the rules in the Pricing/Explain column in the optimization comparison table, a shortened bar appears instead of a price range bar for all rules with equal min and max prices.
The optimization comparison table will always stay open when an ongoing optimization is completed.

2022-12-14

Changed

Display full forecast name in optimizations table.

Fixed

All opened dialogs are closed on logout.
Key section in optimization comparison table always displays all available KPIs.

2022-12-09

Added

Automatically log out if tab is out of focus for 5 minutes.

2022-12-02

Added

Date picker is now available when creating a date-based scope filter. It allows to choose an operator and a value from available dates.
Search terms for exact matching start with '='.
Renaming the optimization settings is possible.

Changed

Adding/editing search terms will open a dialog, instead of in-place inputs.

Fixed

The arrows from compare table are now matching the logic of ordering, up = ascending, down = descending ordering.

2022-11-23

Added

Support exact match when clicking on an item from the compare table

Removed

Remove delete batch buttons and unneeded checkboxes

2022-11-16

Added

New Feature: Pinned optimization settings. For convenience, most frequently used optimization settings can now be pinned to the top of the list, and reused to create new optimizations. Click on the pin icon to the left of an optimization to have its settings always available.
Show loading status for scope filters
Support date scope filters

2022-11-09

remove fallback to main currency for unknown market
Get static asset notifications from http request
Improve backend performance
save timestamp of last read notification
Frontend/use static changelog for notification
fix #11630 - Use static changelog for release notification in frontend
fix #10920 - Remove fallback to main currency for unknown markets

2022-11-02

Backend/fixup 10339
Notifications for changes
add padding right to expand context menu

2022-10-26

Fix unable to refresh backend
Frontend/fix hardcoded key columns
Backend/capture missing column error

2022-10-19

remove header border
Close feedbackform after timeout
Client/configurable integration names
display 2 columns in the dropdowns for the description
add info helptext in optimization form

2022-10-10

Backend/fix 11063 custom csv format
Core/remove partitioned optimization result flag

2022-10-05

client survey
editable dashboard search terms pills

2022-09-29

Re-add cur_price_change in comparison view.
Only replace optimizations table
Core/forecast kpi renaming

2022-09-22

fix #10661 - incorrect date range when submitting opt

2022-09-21

Fix unable to save upload error event
Render histogram only after loading complete
fix #7902 - rename default opt_download table to opt_price_change

2022-09-19

always select present optimization range
fix #10661 - wrong forecast selected for given date range
fix #10642 - Date range is not updated automatically / new dates are not available for selection

2022-09-14

fix #10596 - Date range update still available even without forecast
forecast variant selection
adjust dbt optimizations table
fix #9693 - Enable csv download for snapshots not associated with any integration

2022-09-05

add plausible analytics to app
Remove BCC recipients from reset password email
Add all forecast columns to optimizer result.
fix #7677 - order- and copyable scope conditions

2022-08-30

fix #10259 - current predictions in dashboard not aware of marketing_option

2022-08-12

fix #9927 - Unable to update backend via pipeline
Backend/remove data type checking
Frontend/resolve 9786
Frontend/resolve 9809
Prefer section from kpis.yml over hard-coded front-end config
Frontend/fix 9060 allow saving red entries
fix #9592 - allow analytical function in rules
fix #9220 - Don't add KPIs if they are all NULL OR all default
fix #4758 - Prefill rule value

2022-07-28

Core/add roas kpi
fix #9534 - Veto selection still exists after log-out and log-in.
fix #9522 - Enable Percent formatting like 0.12%

2022-07-14

Do not apply veto to snapshots that don't support it.
Frontend/support (almost) any type search
Update Django and related packages
fix #9371 - Optimization view in front end keeps loading when sorting by boolean column
Optimizer/configurable snapshots
fix #8726 - Restructure download section
fix #8197 - Veto button

2022-07-08

fix #9372 - Positive profit change is displayed with minus in fontend optimization list view
Disable view opt. button on status=progress
Aggregate extreme cur. prices on opt. group level

2022-07-07

use tooltip to show absolute result values
machine-readable, centralized KPI definitions
Frontend better optimizations list
rename opt_download table to opt_price_changes
fix #7845 - More Visual Optimizations Overview Table

2022-06-24

Enable search on opt_id
fix #8953 - No price change scenario displays wAvg Price change higher than 0%
fix #8825 - BQ type specific column formatting

2022-06-17

Move partitioned_optimization_result flag to dbt vars

2022-06-16

Remove legend box border.
Determine opt. colors at time of comparison.
fix #8582 - Add opt legend to comparison
avoid horizontal scroll
Standalone optimization table
fix #8137 - Better product search in compare component

2022-06-07

Frontend/last login fix
Rename 'Current Prices` to 'No Change' in preview.
Rename internal section key from predictions to financials.
fix #8253 - Suggestions for comparison table
fix #2824 - Show do-nothing scenario in comparison automatically

2022-05-19

Improve backend startup performance
Fix optimizer deadlock in the forked process
Add KPIs from latest forecast

2022-05-12

Improve inventory KPI descriptions
Update histogram columns only when extremes not empty.
Log optimizer request for debugging
Serve static files from GCS

2022-05-11

Do not load unavailable columns from cache.

2022-05-11

Check if columns in explicit visible list are available.

2022-05-07

Fix race issues while updating optimizer results
fix #5263 - add optimization group/value to optimization output
Frontend/updade hist kpis

2022-05-04

More price columns in the price section
update kpi definitions
fix #8218 - Enable cpu allocation on production
Frontend/improve compare table
fix #7735 - integrate optimizer into backend

2022-04-21

Only check upload perm when needed and leftover model renaming

2022-04-21

Rename Scenario to Optimization
Fix throwing invalid exception
drop unused libcoinor and deps
Backend/upload role
test background cpu allocation on dev instances

2022-04-04

fix #7868 - position all buttons as sticky column on table end
fix #7190 - Limit histograms in front-end

2022-03-29

fix #7447 - Single click to view optimization
fix #7279 - Better range display on front-end comparison histogram
fix #7768 - Reset table scroll on pagination
fix #7273 - Prefill new optimization with latest from selected group
fix #6841 - Frontend not displaying login error
fix #6433 - Frontend shows [object Object] popup on network errors
fix #5159 - Remove separate turnover target input field

2022-03-24

fix #6974 - out-of-sync dashboard optimization selection
Increase default page size to 50 in compare table.
fix #7468 - overlapping tick labels on compare overview graphs
fix #7017 - Signature verification error during token refresh #7587

2022-03-22

fix #7738 - comparison dashboard mixes up graph order

2022-03-18

fix #7593 - conflicting rule names in different groups
confirm deletion of resources

2022-03-17

fix #7469 - backend matches unrelated tables as forecasts
fix #7240 - stop frontend status updates on logout
fixup #7529 - upgrade to newer pipeline endpoint
fixup #7551 - synchronous backend update from pipeline

2022-03-11

fix #7490 - invalid jwt tokens logged from audit middleware
fix refreshing product filters via admin panel
Update to latest django-ninja v0.17.0

2022-03-07

fix #5948 - fixed comparison table header
centralize error reporting
fix migration without matching forecasts
log password reset mails being sent

2022-02-23

fix #7289 - plenty of bad requests for outdated frontend instances

2022-02-22

fix #6834 - missing rounding for 0% bucket
fix #7215 - error at rule creation in user groups
bump product limit to 500,000

2022-02-18

fix #6233 - modular filter query
fix #6709 - scenario comparison not loading
fix #6725 - Show profit margin on preview tooltip
fix #6993 - Special characters in the product search bar result in an infinite loop

2022-02-10

fix #5728 - negative relative profit change with negative current profit in preview
fix #5831 - add user groups
fix #5905 - configurable optimization up-/download
fix #6775 - add "benchmark" in the list of words that are associated with percentage representations
show predicate and interpolated price in rule admin form

2022-01-21

fix #6317 - update python and deps
fix #6577 - forward-compatible project config deployment

2022-01-14

fix #6361 - same synthesized prices can break interpolation
fixup #3977 - current prices always included as optimization options

2022-01-06

fix #6390 - incorrect number of rules shown in explain column
rename optimal_price to revenue_profit_target

2022-01-04

fix #6359 - Optimal price displayed as current price range bar

2021-12-20

fix #6239 - Optimal price displayed as current price

2021-12-19

implement #3977 - rule prioritisation
implement #6209 - rule explain section
fix #6211 - synth rule opt values break fallback group consistency
fix #6205 - replace opt value hashes with defined strings

2021-12-10

support unknown pipeline config fields in backend runtime config

2021-12-09

fix #6046 - event refresh hitting rate limit

2021-12-02

fix #5939 - frontend removes valid options

2021-11-25

upgrade filter.sql to support string optimization_value

2021-11-23

upgrade backend database to PostgreSQL v13

2021-11-18

fix #5371 - broken table header after drag&drop
fix #5561 - drop embedded datastudio dashboards
fix #5309 - spurious ProgressEvent error toasts
fix #4574 - allow stale scope filter entries
fix #5582 - preview error on submitting copied scenario with invalid rule

2021-11-11

fix #5284 - drop support footer
fix #5293 - use session storage to keep compare forecast KPIs
fix #5379 - renew DB password in time
fix #5589 - Enable OAuth2 username in the auditlog

2021-10-18

fix #5255 - calculate preview points in consistent way with optimizer
fix #5288 - enable Polish locale
fix #5191 - disable comparison if no scenario has been selected
fix #5173 - round to 2 decimal places in preview
fix #5150 - deactivate compare forecast until optimization is finished
fix #5115 - optimization failed yet the status still is processing
fix #5057 - update Angular to v12

2021-10-04

fix #223 - live status updates of optimizations

2021-09-27

fix #4898 - preview broken with nested optimization values

2021-09-16

fix #4865 - optimizer misses few prices due to rounding

2021-09-16

handle mismatched field type and BQ type

2021-09-14

fix #4299 - product-level comparison table
fix #4735 - improve comparison histogram section
fix #4695 - limit compare column widths
validate forms on submit

2021-08-31

fix #4579 - drop project cfg.yml from backend

2021-08-31

fix #4569 - drop project cfg.yml usage from backend

2021-08-27

implement #2888 - configurable optimization upload integration

2021-08-10

fix #4341 - broken upload/synchronize integration deployed to all projects

2021-08-09

fix #4323 - optimizations not saved in BQ due to schema mismatch

2021-08-06

fix #4292 - Render only rule names in filter query

2021-07-27

much faster optimizer (#3493, #3822)
overhauled backend API implementation (#3526)

2021-07-09

fix #3885 - failure when posting scope with multiple and conditions
fix #3856 - renaming scopes leaves cached rules with invalid scope name
fix #3886 - form-select/autocomplete not filtering by displayed value
faster optimizer
faster backend

2021-07-06

fix #3768 - Display norwegian krone on frontend

2021-06-30

fix #3726 - sorting by columns in comparison table not working
fix #3702 - abbreviated select options
fix #3727 - invalid scopes in comparison summary

2021-06-29

flexible scope definition (exclude lists, OR combinator)
fix #3219 - display share KPIs as %
refactor frontend to be simpler and more aggressively cache backend data

2021-06-11

fixup #3167 - fix incorrect preview graph boundaries for fixed price rules

2021-06-09

fix #2418 - list applied rules in optimization comparison table

2021-06-02

fix #3358 - broken password authentication for optimization download

2021-06-01

fix #3347 - dev forecasts published to production instances
fix incorrect elasticity aggregation in optimization download

2021-05-31

fixup #3331 - fix admin scope/filter refresh
list allowed special password characters

2021-05-29

fixup #3269 - fix scope product count with separate forecast tables

2021-05-28

fix #3205 - use separate forecast tables

2021-05-27

include predicted sales in scenario preview and result
improve scenario preview curve

2021-05-21

fixup #3203 - configurable column order of legacy optimization integration

2021-05-18

fix #3199 - historize all forecast predictions in optimization result

2021-05-12

fix #2842 - separately customizable optimization download
fix #3162 - add optional ordered row index to download csv
fix #3160 - configurable csv download line separator

2021-05-07

fix #3123 - boolean scope attribute selection not working

2021-05-03

fix #3060 - KPI formatting fails in comparison table
rename optimizations_download to optimizations_comparison

2021-04-30

followup #2907 - format rate KPIs as percentages

2021-04-28

followup #1535 - strip leading zeros of pasted numeric selections by parsing them as numbers

2021-04-28

fix #2907 - format KPIs in optimization comparison dashboard as percentages or currency

2021-04-23

fix #2949 - percentage categories in histogram are plotted as linear numbers
fix #2889 - unable to remove a scope in some cases
fix #2883 - update forecast information may fail

2021-04-14

implement #2424 - comparison histograms for all optimization KPIs
implement #2361 - add revenue-weighted price change to comparison bar plots
implement #2537 - live-update rule templates

2021-03-31

fix #2686 - too eager predictions rounding in comparison dashboard

2021-03-30

update rule templates
fix #2572 - changing optimization artifacts

2021-03-24

fix small KPI inaccuracies in filter rules

2021-03-23

fix #2580 - preview error with zero revenue/profit

2021-03-10

fix #2287 - handle scope deletion while updating product counts
fix #2393 - allow jagged rows when importing CSV

2021-02-18

fix #2238 - support additional product_attributes in customized optimization download

2021-02-18

fix #1968: missing datastudio dashboards

2021-02-17

redesigned scenario table and support batch actions
new scenario comparison dashboard and direct optimization download via frontend
migrated rule KPIs in forecast (and deploy updated rule templates)
switched from App Engine to Cloud Run on Google Cloud to enable faster deployment

2021-01-06

better automatic testing of rule templates for every forecast and code change (frontend might warn about deprecated rules that need to be updated)
fix #1620 - preview graph outside of x/y-axis for fixed price rules

2020-12-23

fix #1634 - optimization zip upload produces gzip-compressed files
fix #1616 - incorrect or stale product count in scopes

2020-12-16

faster optimization scenario preview for scopes with many options (e.g. hundreds of products)
reworked optimizer to support a lot more products

Frequently Asked Questions

This is a collection of frequently asked questions from our users.

How can I analyze the results of an optimization?

You can check the details of the optimization by clicking on the "eye" icon.

If this is one of the first optimizations you want to upload, it makes sense to check generally if the data seems valid to you. That can include checking the validity of current prices, product attributes, as well as red price discount and voucher levels.

If you are already familiar with optimizations in general and established data quality, it is often useful to analyze the most extreme price predictions by ordering the optimization results by price change, as well as checking the recommendations for high sellers, using the profit and revenue prediction filters. If you want to understand better what led to the price recommendation, you can check the diagram in the "Explain"-column, which will give some context for the recommendation. Lastly, it can be useful to check if there are products at negative margins, and if a price increase is recommended accordingly.

How long are optimization results available?

Old optimizations, comparison tables and uploads are available for two years in the front-end. Forecasts are only available for 3 month, as they take-up a lot of space. To increase data retention times, we can set-up a back-up flow into a cloud bucket in the upload section to save data for more than 2 years.

How do you create an optimization scenario with single or multiple targets?

Access the "Optimizations" page within your domain and click "Create." Provide a name, select the latest forecast, and define the scope for your target. For multiple targets, click "+" to add more targets and specify their respective scopes. You can include pre-defined rules for each target, such as "current price" or "interpolated price" rules. Finally, click "Submit" to create the optimization.

When is the new forecast going to be ready?

The new forecast is ready as soon as our machine learning pipeline to update the forecast ran through. Our pipeline is scheduled to start every day at the exact same time and includes the following steps:

We check the quality of your new data -> data quality issues will delay the pipeline
We train new models based on your new data and test them -> test errors will require a 7L Data Scientist to check
We create a new prediction with the new models and test it -> test errors will require a 7L Data Scientist to check

How can I compare several optimizations?

The compare dashboard enables side-by-side analysis of different scenarios or data sets. For this, simply click the "eye" on more than one optimization at a time. Apply filters based on specific criteria or variables to refine your comparison and focus on relevant information.

How can I schedule an optimization upload?

To schedule an upload, go to the "Upload" page and click the "Create" button. Set the desired upload time (e.g., after 2 minutes). After a short period, you'll receive an email notification requesting approval for the pending upload. Click the link in the email and confirm the upload. The status on the platform will update to reflect the successful upload, and the data will be available for use in optimizations.

Why are some optimized prices outside the requested price range?

The current price is always considered as a potential price point. For example, even if you requested to limit price points below the recommended retail price (RRP), the optimal price may still exceed the RRP if the current price is higher. In this scenario, to ensure that the optimal price remains strictly below the RRP, apply the following rule:

Optimal Price ≤ RRP × 100%

This rule guarantees that the optimal price will never exceed the RRP even if the current price is higher. You can find more information in section Rules.

How can I download optimization data?

To download optimization data, click the upload/download icon located to the right of the eye icon in the Optimization Overview. This will allow you to download a CSV file of the Comparison Table.

How can I get support when using the Pricing Tool?

On the right-hand side of the Pricing Tool, you will find a Help Desk option. From there, you can create a support ticket for our team.

When submitting a ticket, please choose the category that best fits your issue — Bug, Question, or Feature Request — and provide a clear and detailed description. You can also attach screenshots to help us understand the context.

Our team will respond as quickly as possible, and you will receive a notification once we have replied.

How and when can I re-run the pipeline?

You can re-run the pipeline yourself whenever the tool notifies you of a data issue that needs to be fixed. After resolving the issue, you do not need to wait for a data scientist to re-run it for you. Simply go to the Pipeline Status option on the right-hand side of the tool and trigger the re-run from there.

How is the optimal price chosen?

In the Optimization Comparison Overview, under Pricing+, there is a field called "Why this price?". This field explains how the tool arrived at the optimal price for each market–channel–product combination (or other configured levels of granularity).

When you click the icon in this field, you will see:

The current price
The list of allowed prices configured for that product
The pricing rules applied to the product
How each rule affected the allowed prices to determine the final optimal price

How pricing rules are applied:

Rules are applied in priority order, from top to bottom
Higher-priority rules are applied first
Optimization starts with all allowed prices for the product
Each rule filters the remaining allowed prices based on its conditions
The output of one rule becomes the input for the next rule

What happens if a rule removes all prices:

If a rule filters out all allowed prices, the rule is marked as failed
Failed rules can be viewed in the Optimization Dashboard
A fallback rule is then applied if configured

Final price selection: After all applicable rules are processed, the optimization logic evaluates the remaining prices using predicted profit and the configured steering target to select the optimal price.

Why are the rules not applied as I expected?

There can be several reasons why a rule is not applied:

Contradicting rules – Two or more rules conflict with each other. You can quickly identify such “failing rules” by filtering for failing rules in the filter menu.
Price option rejected by a rule for one product in the optimization group – In this case, that price option is immediately removed and cannot be used for any product in the group.
Allowed price range is not sufficient – The range is narrow to set the desired price or apply the rule.

How can I expand the list of allowed price points available for optimization?

There are two ways to introduce additional price points:

Update the allowed price points: if you need to expand the set of allowed price points, please create a support ticket via the Help Desk so our team can update them for you.
Use a price-generating rule: rules that use the “=” operator can generate new price points. For example, you can create a rule that sets the price to Purchase Price × X. This will produce a new price point, which will still follow any rounding rules defined for your allowed price points.

Can I use one rule across several different scopes without creating duplicates?

Yes! There are two ways you can achieve the desired flexibility:

Adjust the scope of a rule directly in the optimization definition.
When creating an optimization, simply click on a rule and select the scope you want to use. This makes it easy to apply the same rule across different scopes.
Group rules together using the grouping option on the right-hand side of the Rule when creating an optimization.
This allows you to combine multiple rules—such as the same rule template applied to different scopes—and use them together within an optimization.

How does the tool handle a product that belongs to multiple scopes?

If a product appears in more than one scope, the tool will display a “scope overlap detected” warning when you run an optimization. In this case, the tool optimizes the smaller (more specific) scope first, and the larger scope will not influence the result for that product.

What is the Optimization Group Identifier in the optimization comparison view?

An Optimization Group is a feature that treats a specific set of products as a single unit during price optimization. It can be a combination of market, channel, product group id, or product id It ensures that the prices of related products move together. The system determines the optimal relative price change (e.g., a 10% decrease) for the entire group, preserving the established price relationships (the price gap) between the items.

How does the pricing work inside an Optimization Group?

The optimizer decides on a single, uniform relative price change for the whole group.

Scenario	Before Optimization	Optimal Change Decision	After Optimization
Product A	$10.00	All products decrease by 10%	$9.00
Product B	$20.00		$18.00

The price difference (e.g., Product B is always twice the price of Product A) is maintained, but all prices shift up or down together based on the optimal decision for the group.

How do my pricing rules affect products within an Optimization Group?

Rules are tested individually for every product, but they impact the entire group's decision.

If a specific price option (e.g., increasing the price by +10%) is rejected by a rule for just one product in the group, that price option is immediately removed and cannot be used for any product in the group.

The final, optimal price change chosen must be applicable to all products in the group without violating any individual product's rules.

How can I include competitor price data in the pricing tool?

You can provide competitor price data as part of the daily import together with your other data tables. The required format and structure are described in Section 3.9, where you will find the full specification for the competitor price table.

Once the data is provided, you can use the existing rules to incorporate competitor prices into your optimization:

Optimal Price ≥ Min Comp Price × value
Optimal Price ≤ Min Comp Price × value
Optimal Price = Min Comp Price × value

These rules allow you to anchor your optimized prices to competitor pricing as needed.

How does the system determine the initial price or discount for a new product with no sales history?

Initially, you can set a starting price and purchase price for the new product. Because the item lacks historical transaction data, the system determines its pricing behavior through a two-stage process:

Cross-Learning: The system identifies "comparable" items already in the system by looking at attributes such as category, season, and brand. It initially assumes that costs and elasticity are similar to these products.
Direct Learning: As the product generates incoming transactions, the model learns from it directly. It then adjusts the initial assumptions to reflect the product's actual performance.

The exact attributes influencing this cross-learning vary by model. If you have insights into specific factors that influence your products' elasticity, costs, or sales, please let us know so we can refine the model.

Can I prevent new products from being discounted for a specific period after launch?

Yes. You can define rules such as "Discount = 0%" for specific scopes (e.g., "New Arrivals") to ensure they remain at the Recommended Retail Price (RRP).

If a "new product" flag is not already available in your data, you can add a custom column to your Product Attributes table (e.g. FLAG_NEW). Using this attribute, you can create a specific scope in the app to maintain a price stability for these items by applying a fixed price or discount constraint.

If a specific rule you require for new products is not available in the tool, you can create a ticket requesting the feature and we will add the rule for you.

AB Group: Field used for testing optimization impact
Active Since: Time at which the values in this row changed as an ISO 8601 UTC timestamp (e.g. 2022-04-24T22:54:51Z)
Active Till: Timestamp until which a KPI had a certain value (ISO 8601 UTC 2022-04-24T22:54:51Z)
Aggregated Sales Difference: Predicted Sales Before Returns over Actual Sales Before Returns
Stock: Stock of the product distributed to one specific market and channel.
Availability: Number between 0% - product not available to purchase and 100% - fully available for purchase
Avg Commission Cost: Cost paid to a third party platform for selling the item on the platform per sold item after returns
AVG Comp Gross Red Price: AVG of all available competitor prices for the product
Conv Fkt To Main Currency: Average factor the foreign currency has to be multiplied with to get to values in the main currency (e.g. 1.2 to get from GBP to EUR). This average is derived from the lastest transactions.
Cost Per Click: Average cost of getting one paid click. 11 EUR marketing cost / 11 paid clicks = 1 EUR avg_cost_per_click
Avg Gross Red Price: The daily average gross red price for which a product was sold (effective price). This value is including tax and is in the original currency
Avg Inbound Cost: Return cost in main currency per returned item
Avg Marketing Cost: Marketing cost in main currency per sold item before returns
Avg Other Cost: All other costs per sold item before returns. This cost has similar behavior as avg_outbound_cost and avg_marketing_cost
Avg Outbound Cost: Cost of sending the product from the warehouse to the customer minus any shipping revenue paid by the customer in main currency. Outbound cost can include logistic cost, shipment cost, call center cost and payment cost
Avg Purchase Price: Historical net cost of 1 good sold (without tax) including shipping cost to the warehouse (e.g. landed cost) in main currency
Avg Raw Margin 365 Days: Average raw margin over 365 days
Raw Profit Margin: Profit Margin after Purchase Cost and before all other costs including vouchers for the products in the optimization
Avg Red Price Discount Spending: The EUR value you spend per (sales_before_returns - returns) for volume discount for example, 10% less if you buy 20 items or more, 3% sconto for paying cash, aftersale discount on red price to avoid a return, customer specific discount for a large customer (e.g. Siemens).
Avg Voucher Spending: The EUR value you spend per (sales_before_returns - returns) for vouchers like newsletter vouchers.
Basket Position: Rank that SKU has in the basket
Benchmark Group: Group of products used to estimate the seasonality of the product and its long-term sales potential. This group is also used to calculate the Benchmark Sell Through Rate.
Benchmark Sell Through Rate: Share of product's Sales Before Returns expected to be sold within the short-term forecast period (default 14 days) divided by Sales Before Returns until the Liquidation End Date
Brand: Name of the brand of the product
Bundle ID: Unique identifier of a bundle of products. Is mapped as product_id in all other tables (i.e. transactions, prices).
Channel: Sales domain where the product was sold (e.g. amazon.de for Amazon sales channel)
Channel Currency: Three letter code for local channel specific currency according to ISO 4217 (e.g. EUR for Euro currency)
Color: Main color of the product
Commission Cost: Net commission costs in main currency paid for selling these products on a third party platform (e.g. Zalando, or Amazon)
Commission Rate: Share of the gross red price spend on commission cost for selling these products on a third party platform (e.g. Zalando, or Amazon)
Commission Rate Start Gross Red Price: Gross Red Price in local currency from which the corresponding commission rate should be applied. The corresponding commission rate will be applied up to the next highest Start Gross Red Price. If no higher Start Gross Red Price is specified, the corresponding commission rate will be applied to all prices higher than that price.
Comp Delivery Time: Number of days the competitor needs for shipping the product to the end customer
Comp Red Price: Gross Red Price after discount including taxes in local currency excluding Shipping Price
Comp Is Active: True if the product is online in the webshop and could be bought by the end customer in that period
Comp Name: Name of the company selling the crawled product
Comp Shipping Price: Price for shipping the product from the competitor warehouse to the end customer in local currency
Competitor URL: Link where the Competitor Price was crawled from
Conv Fkt To Main Currency: Factor the foreign currency has to be multiplied with to get to values in the main currency (e.g. 1.2 to get from GBP to EUR)
Competitor Count: Count how many competitors are in the competitor statistics like the Min Comp Price
Cross Sell Category: Split of products by the amount of avg. cross sell in 5 equally large buckets. Cross sell is calculated as the total revenue from other products bought in the same basket over the last 90 days, after the return period, but only when the product was the basket opener, defined as being in the first basket position in at least three orders.
Cur Bundle Discount: Discount the bundle Gross Red Price has vs. the sum of the Gross Red Prices of the contained products in the bundle
Current Black Price: Current Gross Black Price before discounts including taxes in local currency
RRP: Current Recommended Retail Price (RRP) provided by the supplier of the product in local currency including sales taxes
Current Price: The current gross red price for which a product is sold. This value is including tax and is in the original currency
Current Price Active Since: Date that the Current Price became active
Current Price Online Days: Days that Current Price was online
Current Marketing Option: The latest marketing steering provided
Cur. Marketing Intensity: Current intensity of the marketing steering. The higher the number, the more aggressive the steering and the higher the marketing spend.
Cur Purchase Price: Current net cost of 1 good sold (without tax) including shipping cost to the warehouse (e.g. landed cost) in main currency
Customer Lifetime Value: Incremental future profit increase driven by the transaction in main currency. Is typically higher for new customers and customers with higher repurchase rates.
Date: Calendar day in format "YYYY-MM-DD"
Days since 1st active price: Counts the days since getting the first active price for the product in the market/channel. We use the earliest active price period for the product or the first sale of the product if that happened earlier.
Days since 1st Sale: Counts the days since getting the first sale for the product across all markets & channels.
Days since 1st Sale Category: Categorizes products in age buckets based on the days since getting the first sale for the products.
Discount: (Gross Black Price - Optimal Price) / Gross Black Price
EAN: 13 digit International Article Number (also known as European Article Number)
Liquidation End Date: Date by which the product should reach the Target Sell-Through Rate (e.g. season end date) in ISO 8601 format (i.e. YYYY-MM-DD; e.g. 2025-06-30)
Liquidation End Value: Product's net value in main currency at liquidation end date to calculate the write-off for the seasonal profit calculation. The purchase price is the default value if not specified.
Forecast Date: The forecast's creation date, which is usually also the first forecasted day
Gross Black Price: Gross price before vouchers in local currency including sales taxes
Gross Omnibus Price: This is the lowest price within the last 30 days or NULL if such a price doesn't need to be displayed according to the "Omnibus Directive" (DIRECTIVE (EU) 2019/2161).
RRP: Recommended Retail Price (RRP) provided by the supplier of the product in local currency including sales taxes
Gross Red Price: Gross price after discounts and before vouchers in local currency including sales taxes
Price raw margin 365 days: Gross red price raw margin in the past 365 days
Inbound Cost: Logistic and discard costs in main currency linked to handling these returns.
Is Active: Indicator that determines if the product is available for purchase in the specified period, regardless of stock levels or other factors you are already sending.
Is Own Brand: True if retailer owns the brand
Stock-capped: Boolean flagging indicating if the product sales are limited by the Stock + Stock From Expected Returns. Using stock capping can lead to automated price increases as the optimizer will avoid to run out of stock. e.g. If there is 10 items on stock, we can't predict to sell more than 10 items over the prediction period.
KVI Rank: Ranking of how important a product is for the end customer. Rank 1 identifying the most important product. By default, the ranking is based on historical revenue, the number of competitor prices and the historic margin as KVIs are highly price-sensitive.
Conv Fkt To Main Currency: Latest factor the foreign currency has to be multiplied with to get to values in the main currency (e.g. 1.2 to get from GBP to EUR), on a channel basis.
Live Share: The percentage of products in the optimization for which the optimal price is online.
Main Currency: Three letter code for main currency according to ISO 4217 that we use for revenue summation across channels with different currencies (e.g. EUR for Euro currency)
Market: Country where the product was sold using ISO 3166 format (e.g. DE for Germany)
Marketing Cost: Net marketing costs (SEA, price comparison commission, other advertising) linked to these sales after returns
Marketing Option: Marketing steering that led to the clicks/traffic during a period of time
Campaign Type: Description of the campaign type used to steer the marketing intensity. We support "CpC" in which case marketing_option_float is the Cost per Click steering, "tROAS" in which case marketing_option_float = 100 / tROAS (e.g. 0.25 for a 400% tROAS), "ACoS" in which case marketing_option_float is Advertising Cost of Sale = Marketing Cost / Revenue (e.g. 0.25 for a 25% ACoS)
Marketing Intensity: The intensity of the marketing steering (e.g. 0.7 for 70 cent max cost per click campaigns OR 0.25 for 25% ACoS OR 0.25 for 400% tROAS)
Max Comp Gross Red Price: The maximum competitor price crawled for this product
Max Comp Names: Name of companies offering the most expensive price for the product
Med Comp Gross Red Price: Median of all available competitor prices for the product
Min Comp Gross Red Price: Minimum competitor price for the given market and product during that period
Min Comp Names: Name of companies offering the cheapest price for the product
Min Competitor Price: Smallest Gross Competitor Price in local currency
Name: Name of the product
N-th Most Recent Price Change: The n-th most recent competitor price period for the given market and product (newest period is 1st)
Optimal Price: Optimal Gross Price in local currency for the given rules and targets
Competitive Positioning: Optimal Price / Min Competitor Price -1
Optimization ID: Unique identifier of the optimization
Optimal Marketing Option: The recommended marketing steering
Opt. Marketing Intensity: Optimal intensity of the marketing steering. The higher the number, the more aggressive the steering and the higher the marketing spend.
Opt Name: Name of the optimization given by the user
Optimization Group: Combination of Product ID, Market and Channel which should receive the same optimization result.
Optimization Value: Description of the option that was available for the optimizer to chose from. e.g. price 29.99 EUR
Order ID: Unique identifier for the order to which the product belongs
Order Quantity: The amount of products we recommend to order over the selected period of time
Order Value: The value of the order quantity in terms of purchase_price.
Other Cost: Other costs in main currency you consider in your profit calculation for these sales
Outbound Cost: Costs in main currency of sending these products from the warehouse to the customer. You can add logistic cost, shipment cost, call center cost, and payment cost. And you can subtract shipping revenue paid by the customer.
Paid Clicks: Number of visits from paid sources
Picture: URL to a Thumbnail of a product picture. Common thumbnail sizes include 75x75, 100x100, 150x150, and up to 300x300 pixels. Typical sizes ranging from 10 KB to 50 KB.
ACoS: Advertising Cost of Sales, (ACoS), is a marketing metric that measures the efficacy of a digital advertising campaign. It's calculated as Marketing Cost / Revenue Before Returns
Commission Cost / Sale: Predicted cost paid to a third party platform for selling the item on the platform per sold item after returns
Conversion Rate: Predicted Sales Before Returns / Predicted Clicks
Cost per Click: Predicted Marketing Cost/ Predicted Paid Clicks in main currency
Customer Lifetime Value: Incremental future profit increase by sales before returns in main currency. Is typically higher for new customers and customers with higher repurchase rates.
Elasticity: Predicted change of demand over change of price from current to optimal using the midpoint formula ((q2-q1)/((q2+q1)/2))/((p2-p1)/((p2+p1)/2))
Gross Red Price Prior Season: Average gross red price in the preceding period.
Inbound Cost / Return: Predicted cost if customer returns one product in main currency
Liquidation End Profit: Sum of profit from sales until Liquidation End and write-offs from stock left-over at the Liquidation End date
Liquidation End Profit Impact: Difference between the predicted Liquidation End Profit after optimization vs. the predicted Liquidation End Profit before optimization.
Liquidation End Profit Optimization Group: Sum of net profit from sales until Liquidation End and write-offs from stock left-over at the Liquidation End date for all products in the Optimization Group
Liquidation End Stock: Predicted amount of left-over stock at the Liquidation End Date in the specific market-channel
Marketing Cost / Sale: Predicted Marketing Cost / Predicted Sales Before Returns in main currency
Net ACoS: Net Advertising Cost of Sales, (Net ACoS), is a marketing metric that measures the efficacy of a digital advertising campaign. It's calculated as Marketing Cost / Revenue After Returns
OOS Factor: Sales Weighted OOS Factor. It is used to correct the sales from last season in the order optimization.
Other Cost / Sale: Predicted other costs per sold item before returns in main currency. This cost has similar behavior as avg_outbound_cost and avg_marketing_cost
Outbound Cost / Sale: Cost of sending the product from the warehouse to the customer minus any shipping revenue paid by the customer by product in main currency. Outbound cost can include logistic cost, shipment cost, call center cost and payment cost
Price Change Impact Factor: Price Change Impact Factor is the predicted sales impact by optimizing prices. It is used to correct the sales from last season in the order optimization.
Profit Margin: Predicted Profit Margin after all predicted costs and vouchers for the products in the optimization
Promotion Rank: Ranking of Products/Optimization Groups by suitability for a promotion campaign. By default, it is based on Stock Reach and historic Profit/Sale. However, the exact calculation method can be adjusted. As an example, "Promotion Rank <= 100" will select the 100 Products/Optimization Groups most recommended for a promotion in a given sales channel.
Red Price Discount Rate: Predicted share of revenue after returns spend on red price discounts in percent (e.g. 3% for paying the order in advance)
Red Price Discount Spending / Sale: Predicted amount of revenue after returns spend on red price discounts
Return Rate: Predicted Returns / Predicted Sales Before Returns in %
Revenue per Click: Predicted Revenue per Click in main currency
ROAS: Return On Advertising Spend, (ROAS), is a marketing metric that measures the efficacy of a digital advertising campaign. It's calculated as Revenue before Returns / Marketing Cost
Sales until Liquidation End: Predicted amount of Sales after Returns to be sold until the liquidation end date from the start of the forecast period
Salvage Value Percent: Percentage of Purchase Price that is left of the net product price after subtracting all inbound and outbound related costs. (Net Price - (Inbound Cost + Outbound Cost)) / Purchase price
Stock From Expected Returns: Stock expected to be available from returns of sales in the last 60 days
STR Liquidation End: Predicted Sell Through Rate (STR) the product will reach at the Liquidation End.
Voucher Rate: Predicted share of net revenue after returns spend on vouchers/coupons in percent
Voucher Spending / Sale: Predicted amount of revenue after returns spend on vouchers/coupons
Clicks: Predicted Clicks on the product
Commission Cost: Predicted sum of net commission cost paid for selling these articles on a third party platform (e.g. Zalando, or Amazon) in main currency
Customer Lifetime Value: Predicted incremental future profit increase driven by the transaction in main currency. Is typically higher for new customers and customers with higher repurchase rates.
Inbound Cost: Predicted cost for returns in main currency
Marketing Cost: Predicted Marketing Cost in main currency
Stock At Optimization Start: Remaining Stock at the beginning of the optimization period selected in the Steering.
Sales until Opt Start: The amount of Sales After Returns we predict from the first day of the forecast until the start of the selected optimization period
Stock Reach Weeks Ordering: Prediction after how many weeks the product is running out of stock based on the optimal gross_red_price.
Organic Clicks: Predicted number of visits from sources without direct marketing cost (e.g. direct mail, traffic without marketing cost)
Other Cost: Predicted Other Cost in main currency
Outbound Cost: Cost of sending the product to the customer minus any shipping revenue paid by the customer in main currency. Outbound cost can include logistic cost, shipment cost, call center cost and payment cost
Paid Clicks: Predicted number of visits from paid sources
Profit: Predicted Net Profit in main currency
Profit Margin: Predicted profit margin.
Profit Optimization Group: Sum of net profit after all predicted cost in main currency for all products in the optimization group over the optimized date period
Profit: Predicted Net Profit in main currency
Purchase Cost: Predicted Sales Before Returns * Purchase Price provided for prediction in main currency
Red Price Discount Cost: Predicted Sum of additional discount spending in main currency on top of vouchers and discounts (e.g. 4 EUR customer specific rebate)
Returns: Predicted Items to be returned by the customer
Revenue: Predicted Net Revenue in main currency
Revenue: Predicted Net Revenue in main currency
Sales After Returns Prior Season: Sales after returns in the preceding period.
Sales Before Returns: Predicted Sales Before Returns for the products in the optimization during the optimization period
Sales Before Returns: Predicted Sales Before Returns for the products in the optimization during the optimization period
Voucher Cost: Predicted Cost for vouchers/coupons in main currency
Prev Gross Red Price Ordering: Weighted 365 day average of the product's gross red price used as baseline for the predictions.
Price Change: Difference between the optimal and current prices in %.
Price Change Direction: Direction of price change for optimal price compared to current price. Price Increase if optimal price is higher than current price, Price Reduction if optimal price is lower than current price. No Change if optimal price is equal current price.
Price Change Ordering: Difference between the optimal price and the Prev Gross Red Price Ordering in %. This gives an indication how the long-term historic price should change for the next ordering period.
Producer: Manufacturer of the product
Product Category 1: Top-level category the product belongs to (ideally less than 20 distinct category values)
Product Category 2: Product sub-category the products belongs to
Product Category 3: Product sub-sub-category the products belongs to
Product Group ID: Marks products belonging together (e.g. across sizes) - can be used for prices to move in the same direction
Product ID: Unique identifier of the product or SKU
Product URL: URL where the product can be found
Profit: Net profit in main currency after all delivered costs
Profit Accuracy: Sum of predicted profit in the optimization divided by the sum of the actual profit over the same period of time. Values close to 100% indicate good predictability.
Profit: Sum of net profit after all predicted cost in main currency for all products in the optimization over the optimized period
Profit Impact: Difference between the actual (realized) profit and what the profit would have been without the optimization.
Profit Margin: Predicted Profit Margin after all predicted cost in % for the products in the optimization over the optimization period
Promotion Name: Name of the promotional activity
Promotion Names: Array of names of the promotional campaigns, as there could be multiple campaigns running at the same time.
Purchase Cost: The sum of net landed cost of all products sold in the transaction, including freight cost from the production facility to the warehouse, customs duties, tariffs, insurance, handling fees, and any other import-related expenses in main currency (i.e., COGS or cost of goods sold).
Purchase Price: Net landed cost of a single unit sold, including freight cost from the production facility to the warehouse, customs duties, tariffs, insurance, handling fees, and any other import-related expenses in main currency (i.e., COGS or cost of goods sold).
Purchase Price Category: Split of products by purchase price in 5 equally large buckets
Red Price Discount Spending: The total net value of extra discounts (e.g., customer-specific rebates) in the main currency, other than voucher spending.
Returns: Number of items returned
Revenue: Net revenue in main currency after returns, vouchers, and discounts
Revenue 12 Month: Sum of net product revenue of market & channels in the forecast in main currency after returns from 2-14 month ago (to wait for returns)
Revenue: Sum of net product revenue in main currency after returns (if available) without customer payments for the delivery/return of the product
Revenue Before Returns: Net revenue before returns in main currency after vouchers, and discounts
Revenue Impact: Difference between the actual (realized) revenue and what the revenue would have been without the optimization.
Sales Before Returns: Predicted Sales Before Returns for the products in the optimization during the optimization period
Sales Before Returns: Number of non-cancelled items ordered (e.g. 2 if two items were ordered)
Sales Accuracy: Sum of predicted sales before returns in the optimization divided by the sum of the actual sales before returns over the same period of time. Values close to 100% indicate good predictability.
Sales Before Returns Change: Change of sold items predicted for marketing/price change in % (Capped between -500% and 500%)
Scope: Scope(s) which the product is part of
Season: Main sales period of the product (e.g. summer, winter, ...)
Sell Through Rate: (Sales after Returns since Liquidation Start Date - Stock From Expected Returns)/ (Sales after Returns since Liquidation Start Date + Stock) - for the Optimization Group of the product.
Sell Through Rate Target: Share of Stock that should be sold out at Liquidation End Date
Shelf Location: Row in an offline shelf where product is usually placed
Size: Size of the product
Liquidation Start Date: Date from which the Sell Through Rate of the product is calculated (e.g. season start date) in ISO 8601 format (i.e YYYY-MM-DD; e.g. 2025-03-01)
Stock Change: Changes to your inventory in the future (e.g. restocking, write-offs, and other inventory adjustments)
Stock Reach Weeks: Prediction after how many weeks the product is running out of stock
Stock Start Of Day: Number of items available for sale in the beginning of the day
Tax Rate: Rate of sales tax used to calculate net revenue from gross price. This value must be provided as a decimal (e.g. 0.19 for 19% for most products in Germany)
Time: Date and time when the items were ordered as an ISO 8601 UTC timestamp (e.g. 2024-02-06 22:54:51+00:00)
Total Clicks: Total number of visitors to the product's dedicated detail page from paid and unpaid sources (decimal in case several products share traffic)
tROAS: tROAS (Target Return on Ad Spend) is a bid strategy used in digital advertising where you can set a desired return on ad spend as a percentage. tROAS = Revenue Before Returns/Marketing Cost
Upload Channel: The sales domain where prices will be uploaded (e.g., amazon.de for Amazon sales channel). This is used to distinguish the primary channel in the optimization process from any additional sub-channel where prices are uploaded (e.g., zafr for Zalando France if optimized prices should be sent via an API call to tradebyte).
Upload Conv Fkt To Main Currency: The factor by which the foreign currency has to be multiplied to convert to values in the main currency (e.g., 1.2 to convert from GBP to EUR). This is used to differentiate conversion factors from any additional sub-channel definitions.
Upload Currency: The currency code according to ISO 4217 format (e.g., EUR for Euro). This is used to differentiate the channel currency from any additional sub-channel definitions.
Upload End Date: The day on which the optimization effectively ended, either because the optimization end date was reached, or because subsequent optimizations took over.
Upload Market: The country code according to ISO 3166 format (e.g., DE for Germany). This is used to differentiate the market ISO code from any additional sub-channel definitions.
Upload Start Date: The day on which the optimization was uploaded.
Voucher Rate: Share of net revenue after returns spend on vouchers/coupons in percent
Voucher Spending: Sum of net voucher spending after returns in main currency (e.g. 5/(1+0.19)=4.2 EUR voucher for newsletter).

Changelog

Scopes are groups of products in specific markets and channels that can be defined using product attributes, markets, channels and even predicted KPIs. A scope allows you to manage and optimize these groups individually, enabling more targeted pricing strategies for enhanced performance.

Scopes can be created using filters you provide, such as product attributes, stock level, or other relevant criteria. By combining these filters with logical operators (e.g., "AND", "OR"), you can define specific groups for optimized pricing actions.

Create Scopes

To create a scope, navigate to the scope section, click on "Create", name your scope, set the filters, and then submit.

alt text

Once a scope is created, you can edit, copy, delete, or download it as needed.

Key Scopes Usage

Custom Rules per Scope: Easily define and execute rules that apply only to a particular scope, such as excluding products from price changes or focusing on inventory liquidation.
Segment-Specific Optimization: Tailor your pricing strategy to the needs of individual scopes to meet different business objectives.

Examples of Common Scopes

Sales Channel Scopes: Differentiate products based on sales channels (e.g., Zalando, Amazon). This enables creating pricing strategies that consider the unique dynamics of each channel.
Seasonal Scopes: You can create a scope based on the seasonal demand (e.g., holiday products, summer collections). This helps in adjusting pricing strategies according to seasonal trends and consumer behavior.
Blacklisted Items: This scope includes products where no price changes should occur. Blacklisting items ensures that they are excluded from any automatic pricing adjustments.
Inventory Level Scopes: Group products based on inventory levels (e.g., overstocked, low stock). This can inform discounting strategies to manage inventory effectively.

Conclusion

Defining and managing scopes helps your business handle complex portfolios more effectively, enabling flexible pricing strategies that support your goals.

Elasticity

A product's price elasticity of demand is a measure for how much the demand for it reacts to a change in its price. There are multiple definitions for measuring elasticity.

Example:

\begin{align} Price_1 &= P_1 = 100\ EUR \\\\ Price_2 &= P_2 = 120\ EUR \\\\ Demand_1 &= D_1 = 34\ Sales \\\\ Demand_2 &= D_2 = 26\ Sales \\\\ \end{align}

\begin{align} Simple Elasticity = \frac{(P_2-P_1) / P_1}{(D_2-D_1) / D_1} &= \frac{(120-100) / 100}{(26-34) / 34} &= -0.85 \\\\ Elasticity = \frac{(P_2-P_1) / \frac{P_1+P_2}{2}}{(D_2-D_1) / \frac{D_1+D_2}{2}} &= \frac{(120-100) / \frac{100+120}{2}}{(26-34) / \frac{34+26}{2}} &= -0.68 \\\\ \end{align}

Our Elasticity KPI is using the second elasticity definition, which is often referred to as "Mid Point Elasticity". The advantage of this definition is that going back from $P_{2}$ to $P_{1}$ will give you the same elasticity, so it is symmetric. Also, the Simple Elasticity often comes up with very large elasticity outliers which are difficult to interpret.

We learn Elasticity on market, channel and product level based on product specific price change history and based on product attributes. If we don't have any information on the product specific price history, we approximate it using similar products. To ensure that we capture the true relationship between price changes and sales, we automatically detect seasonal patterns - like summer or holiday trends - and correct the data accordingly. For example, the sales of a seasonal product like sandals, which sells well in summer but less in winter, are smoothed out to account for their summer peak before calculating elasticity.

Forecast variants

Forecast variants enable to simulate and analyze the effects of different forecast configurations. The default forecast, called Main, is generated daily through the daily pipeline run, after receiving the updated data.

Additional forecast variations include voucher rate variants and dev forecasts.

Voucher rate variants

These variants help to evaluate and compare the effect of various voucher rates and determine the optimal prices of the products alongside the selected voucher rate. For example, if a voucher campaign is planned for a specific group of products, forecast variants allow you to simulate different scenarios, such as 10% or 15% voucher rates, to understand which rates are more likely to meet your business targets. This helps to identify the most profitable pricing strategy to achieve higher revenue or profit.

How to use voucher variants:

Define a scope for the products included in the voucher campaign.
Create an optimization, selecting a forecast variant with your chosen voucher rate (e.g: 5%).
Optionally, create additional optimizations with other voucher rates (e.g., 10%) to compare results.
Compare the predicted KPIs on the comparison dashboard.
Upload the prices that align with your business goals.

How to set up:

If forecast variants are not yet available in your frontend and you would like to try out this feature, please contact a data scientist. In your request, specify the desired voucher rate options (e.g., 5%, 10%, 15%, 20%).

Dev forecasts

These forecasts are versions in development that contain new changes or updates not yet part of the Main forecast. These variants can be made available on the frontend for testing, allowing you to compare optimization results between the Main forecast and the updated versions.

New Optimization

This section describes how to create a new optimization in our app.

Option 1: Copy from old optimization You can create optimizations from an existing optimization by clicking the "Copy Optimization" button. This will copy:

The scopes of the old optimization
The rules of the old optimization
The targets of the old optimization

alt text

Option 2: Create new optimization You can create a new optimization by clicking on the "+ Create" button in the optimization section. This will open a new form for creating an optimization.

alt text

Optimization Configuration The optimization for lets you configure the following parameters:

Name: A recognizable description for your optimization. You can change the name later on by clicking on the name in the optimization list
Date Range: Select which days you would like to make an optimization for. Set automatically to the current date until the last available date of the forecast
Forecast Variant: Your 7L Data Scientist can create additional forecast variants for special purposes like 20% voucher campaigns on all products
Last Data Update: Indication when we last updated your forecast
Rules: New rules can be set-up in the Rules section of the front-end and added to an optimization here. Rules can be prioritized with drag and drop. Rule #1 has the highest priority
Scopes: Combination of market, channel and product_id that you want to use for your target setting
Target: Please decide which target type we should persist when we use the optimization settings next time

alt text

Optimization Comparison

This section describes how to compare two optimizations in our app.

Open Compare Dashboard

To open the Compare Dashboard please click the "View Optimization" eye in the Optimizations section. To compare a second optimizations with the first one, just click the eye of the second optimization as well.

alt text

Histogram

To histogram section enables to visualize the distribution of your optimizations for all columns of the compare table. You can see all available columns by clicking on "Other" below the histogram on the right side.

alt text

Filter

You can filter the product specific table by clicking on the filter symbol or by entering a text into the search field.

alt text

Column Customization

You can configure which KPIs you would like to see in your dashboard by clicking on the "+" next to each section.

alt text

Targets

The target selection enables you to decide which target you would like to persist in the long-run for your product scopes. The selected target will be used every time we rerun the optimization settings.

	Angle	Range	Excellence
Profit Margin	Changing	Min Margin-Max Margin	★
Profit Maximum	Constant	Max Profit	★★
Profit Weight	Constant	0% - 100%	★★
Δ Profit / Δ Revenue	Changing	-∞ to +∞	★★★

Profit Margin enables you to steer towards a specific profit margin for your scope. The steering angle where this target is reached will slightly changed based on our predictions. The highest allowed profit margin is the margin at the Max Predicted Margin point, to ensure target uniqueness. The lowest allowed profit margin is the profit margin at the Max Predicted Revenue point. Both points will be influenced by the rules you are using.

Example: "Profit Margin 10%" will always select the point in the curve where your margin is closest to 10%
Profit Maximum enables you to steer towards the point that maximizes short-term profit for each individual product within the scope. When rerunning the optimization, the Max Predicted Profit target will be selected.

Example: "Profit Maximum" will increase the price of a product to 19.99 as we predict that the profit of the product will be maximized at this price.
Profit Weight enables you to select a specific point between the point that maximizes revenue and profit. When rerunning the optimization, the target closest to the Profit Weight target will be selected.

Example: "Profit Weight 50%" will select the point of the curve just in the middle of the profit maximization point and revenue maximization point.
Δ Profit / Δ Revenue enables you to specify, how much profit you are willing to gain/lose for gaining 1 additional revenue. When rerunning the optimization, the maximum profit solution with the Profit-Revenue-Slope closest to your target will be selected.

Example: "Δ Profit / Δ Revenue -0.2" will select the point of the curve where you invest 0.2 profit to gain 1 revenue

Optimization KPIs

Next to the Target KPIs, you can add additional KPIs to the preview curve to be informed about the impact of your target setting on the optimization result. This should enable you to select better targets for your optimization. To configure which Optimization KPI you would like to see, please use the settings button below the curve.

preview_kpi_image

The following KPIs are available

Rules

Using Rules, you can set specific constraints on the options you want to allow. These constraints help filter out any unsuitable options, ensuring that only those that meet your criteria are considered. You can apply optimization rules at a scope level. For example, if you want to ensure that all discounts are below 50%, you can create the rule "Discounts <= 0.5."

Create Optimization Rules

To create a new optimization rule or modify an existing one, navigate to the Rules tab. Click on "Create," and you will be able to choose from a list of predefined rule templates. Once you've selected the rule, define its value, specify the scope it should apply to, and click "Create."

alt text

After creation, you'll be redirected back to the Rules tab, where you can optionally add a comment. From this tab, you can always view, modify, or delete your existing rules.

Use Optimization Rules

When you create a new optimization, you can select from the previously created rules to apply them.

alt text

Once the optimization is complete, you can analyze the effect of each rule on the price options for various market, channel, and product combinations. To do this, go to the optimization, and under the "Pricing+ -> Explain" column, click on the product you are interested in. This will display how each rule impacts the price options.

alt text

Additional Details

If no price option satisfies a specific rule that was selected during optimization, the closest price option to the rule's threshold will be selected as a fallback. It is important to note that the order of the rules determines their priority. The first rule is applied first, followed by the second, and so on.

Conclusion

Optimization rules allow you to set constraints on price options, ensuring that only those meeting your criteria are considered. As a result, all unsuitable price options are automatically filtered out.

Stock

Our stock handling ensures that your available product inventory is efficiently among all your markets and channels. This maximizes your sales opportunities and helps prevent out-of-stock situations.

How Does Stock Handling Work?

When you have a single pool of product stock (e.g., all units in one warehouse) that needs to be shared across multiple locations, we automatically distribute it based on sales predictions and actual item quantities.

Example

Let's say you have 100 total items of Product A available globally.

Location	Sales Prediction	Distributed Stock
Germany	60 sales	60 items in stock
Italy	40 sales	40 items in stock

Forecast setting: Stock Capping

If you frequently run out of stock or have trouble with overstock, it might make sense to consider stock in your optimizations. We offer multiple options for considering stock.

By default we assume unlimited stock in our predictions. Even if you have only 10 items on stock, we would predict 20 sold items for the next 14 days, assuming that you are able to restock the item during the 14 days.
Your Data Scientist can turn-on stock capping in the forecast which then limits the sales to the items on stock (10) plus the expected stock from returns. This would then automatically increase the price on items with low stock also without the use of a rule.

Rule: Stock Reach in Weeks ≤ Value

This rule can be used to reduce the price on a product. Attention: This rule should always be combined with a rule that sets a min margin like "Profit Margin ≥ Value"

Definitions

Stock Reach in Weeks: 7Learnings price on how many weeks the current stock will last at the selected price

Example
Value = 4
Resulting rule: Stock Reach in Weeks ≤ 4

Stock Reach in Weeks example 1

Rule: Stock Reach in Weeks ≥ Value

This rule can be used to increase the price on a product automatically in order to make sure the stock lasts a certain amount of weeks.

Definitions

Stock Reach in Weeks: 7Learnings price on how many weeks the current stock will last at the selected price

Example
Value = 4
Resulting rule: Stock Reach in Weeks ≥ 4

Stock Reach in Weeks example 2

Liquidation End STR ≥ Value

The rule will ensure a target Sell Through Rate (STR) at the liquidation end date. It will push the prices of the products to have a specified STR at the end of liquidation.

Attention: This rule should always be combined with a rule that sets a min margin like "Profit Margin ≥ Value"

Definitions

STR: Measures the liquidation percentage of sold inventory compared to the total stock available over a specific period of time. A high sell-through rate usually means strong demand or effective pricing while a low sell-through rate might indicate overstocking, poor demand, or pricing issues.

Example
Value = 80%
Resulting rule: Liquidation End STR ≥ 80%

Liquidation END STR example

Liquidation End Profit

If you provide us with a Liquidation End Date, we can predict profit at this liquidation end date including write-offs on any stock left at this time.

Sales until Liquidation End

To predict the Sales until Liquidation end we take the predicted sales from the optimization and divide it by the Benchmark Sell-Through Rate. This rate compares sales performance from the same period last year (covering both the short-term forecast and the period leading up to the liquidation end date). The benchmark sell-through rate is calculated for products grouped into Benchmark Groups. For example, if you have a seasonal product category, your Data Scientist can define this category as a Benchmark Group.

Example
Products in Benchmark Group 'summer-tshirt' Liquidation end date = '2025-09-30'

Last year's Sales (optimization period): 100
Last year's sales (until '2024-09-30'): 850

Benchmark Sell-Through Rate would be 100/850 = 11.76%

Assuming Product A in 'summer-tshirt' group

Predicted Sales in Optimization: 6
Sales until Liquidation End Date: 6 / 11.76% = 51

Liquidation End Profit

Definitions
You can find all the referring KPIs in the Inventory section of the Optimization.

Sell Through Rate Target: Set your target for the percentage of stock you want to sell by the liquidation end date. Example: Sell Through rate Target is 80%, for a Stock of 100 products, 80 products will be aimed to be sold at the end of the season
Liquidation End Value: Is the set write-off price for your products at the end of the liquidation period.
Liquidation End: Is a date at which you would like to sell-off a product which could be the end of the season or the best before date
Liquidation End Profit: Sum of profit from sales until Liquidation End and write-offs from stock left-over at the Liquidation End date.

Liquidation End Profit = Profit in season + Profit at Liquidation End Date
Max Liquidation End Profit: The highest Liquidation End Profit available in the prediction among all price/marketing options

Liquidation End Profit Calculation

Profit in Season (at the price of 91.49€): Profit per product x Sales until Liquidation End.

Example 26.35€ x 1791.78 = 47,211.6€

Profit at Liquidation End (at the price of 91.49€): Remaining stock x (Liquidation End Price - Purchase Price).

Example 1904 x (8.92€ - 29.75€) = −39,660.32€

Total Liquidation End Profit (at the price of 91.49€):

Example 47,213.41€ - 39,660.32€ = 7,551.28€ Max. Liquidation End Profit example 1

Rule: Reach Max Liquidation End Profit x Value

You can use this rule to avoid moving too far away from prices that maximize your long-term profitability.

Example
Liquidation End Profit Max = 11,481.37 EUR (at the price of 83.49 EUR)
Value = 60%
Resulting rule: Liquidation End Profit > 6,888.82 EUR
This will force the optimizer to only allow prices and marketing options where the predicted Liquidation End Profit is bigger

Max. Liquidation End Profit example 1 Explain

Bundles

We define bundles as products that contain a combination of multiple other products.

Example

1 Pack of Aspirin Complex -> individual product
3 Pack of Aspirin Complex -> bundle product

Typical bundle issues

The Price of the bundle product should follow the price of the individual product. Example: If the 1 Pack Aspirin Complex is reduced in price by 10%, you need to make sure, that the 3 Pack Aspirin Complex is still more affordable
Stock is usually not stored separately for bundles. Stock therefore needs to be considered virtually for bundles. Example: if you have 10 packs of Aspirin Complex left, you can only sell a maximum of 3 bundles of 3 Packs of Aspirin Complex

Bundle data feed

To better handle bundle products, we ask for bundle information in a separate data feed. The way we ask for the data means, that each bundle will have a bundle_id AND a product_id.

Column	Data Types	Description
product_id	Text	Unique product identifier
bundle_id	Text	Unique bundle identifier
product_qty	Integer, Decimal	Product quantity in bundle

This data feed enables specific bundle rules that wouldn't be possible without it.

Rule: Bundle Price = Product Prices x Value

This rule sets the bundle price at a multiple of the price of the individual products.

Example
Price of 1 pack of Aspirin Complex after optimization = 11.49 EUR
Value = 95%
Price of 3 pack of Aspirin Complex after optimization: Bundle price = 11.49 x 3 x 95% = 32.75 EUR

Rule: Bundle Price < Product Prices x Value

This rule sets a maximum bundle price at a multiple of the price of the individual products.

Example
Price of 1 pack of Aspirin Complex after optimization = 11.49 EUR
Value 95%
Price of 3 pack of Aspirin Complex after optimization: Bundle price < 32.75 EUR

Product Groups

Product Groups give products, that belong together, one identifier in order to be optimized together. This helps keeping price distances within the group logical.

Example

Aspirin Complex 20mg
Aspirin Complex 40mg
Aspirin Complex 60mg

Typical issue with product groups

The Prices of the products in a product group should be connected Example: If the price of "Aspirin Complex 20mg" is going down 10%, so should the price of "Aspirin Complex 40mg" to avoid a lower price per mg of the 20mg pack

Product Attribute data feed

To better handle product groups, we ask for the column "product_group_id" in the product attribute feed.

Column	Data Types	Description
product_id	Text	Unique product identifier
product_group_id	Text	Unique group identifier

This data feed enables to optimize the group together.

Optimization: Example

This rule sets the bundle price at a multiple of the price of the individual products.

Example

Product Name	Product ID	Product Group	Price Change
Aspirin Complex 20mg	660020	PG6600	+13%
Aspirin Complex 40mg	660040	PG6600	+13%
Aspirin Complex 60mg	660060	PG6600	+13%

Further Details

Sometimes, you will have a logical product group like in our Aspirin example, but you still might want the prices to diverge, e.g. because you have separate suppliers for some of the products with independently changing purchase prices. In this case, if you still generally want to use the product group, we would recommend incorporating the supplier into the product group definition so the products with the same supplier can still move together.

The product group moving by the same percentage supersedes other rules if they should be at odds.

If you optimize a subset of the product group in a separate optimization, this will break the common pricing of the products, so be aware of that. If you intend a different steering for some products within a product group, you can achieve that by applying a different target steering within the same optimization.

Promotions

Promotions are more successful, if the preparation follows this three step approach:

Gather historical data of promotion and their impact on sales and profitability
Predict alternative scenarios for the future promotions using this historical data
Decide on one promotion scenario that best fits the goal of the promotion

Types

We currently support to create scenarios for the following promotion types:

Voucher: e.g. 20% on all products in the shop
Discount: e.g. up to 70% discount on selected products
Performance Marketing: e.g. Google Shopping campaign

Settings

Expectations for promotions differ substantially from expectations outside of promotions, which is why we recommend to to run them with different rules and targets.

	Recurring Optimizations	Promotion Optimizations
Scopes	All products	Selected promotional scope
Rules	As little rules as possible	Constrains for promotions e.g. Discount > 20%
Targets	More focus on profitability e.g. "Max Profit"	More focus on Revenue e.g. "Profit Weight 50%"
Forecast	Main/Pricing forecast with normal voucher level	Use voucher scenarios like "10% Voucher Spending" if applicable
Date Range	2 week date range	specific dates of the promotion
Uploads	Scheduled uploads	Manual one-time upload

Promotion Scope

To select the products that should be in a promotion, we recommend creating a specific promotion scope in the "Scope" section. We provide a large range of options to select the products for a promotion:

Select market, channel and an entire product category
Select market, channel and specific products using their Product ID
Select market, channel and an entire brand
Select market, channel and Promotion Rank < 100 to use the 100 most recommended products
Create a custom filter by using important KPIs like Sell Through Rate, Season, Liquidation End Stock or STR Liquidation End

Performance Marketing Optimization

Performance Marketing optimization helps you make data-driven decisions to enhance campaign performance on platforms like Amazon and Google Shopping. Our tool not only collects and analyzes your data but also simulates different marketing scenarios to ensure your products are placed in the most effective campaigns. This strategic structuring allows Google and Amazon algorithms to further optimize within their framework.

Our tool structures campaigns in the best possible way from the outset. By setting revenue and profit targets, you receive data-driven recommendations on how to allocate marketing efforts for maximum impact. This ensures each product is assigned to the most suitable campaign before platform-specific optimizations take place.

Analyzing Your Marketing Campaign Data

Our tool integrates directly with marketing platforms via API to gather key traffic data, including:

Organic and paid clicks
Conversions
Marketing spend
Competitor prices

Additionally, we leverage data already used for price optimization, such as return rates, outbound costs, and stock availability, to provide a comprehensive view of your marketing landscape. Instead of manually compiling and analyzing data, you gain clear, actionable insights.

Forecasting Different Marketing Scenarios

Once your campaign data is collected and refined, our tool analyzes the impact of various marketing strategies. You can test different goal settings (e.g., maximizing revenue or profit) and see how they affect:

Traffic and conversions
Click-through rates (CTR)
Cost per click (CPC)

By evaluating different scenarios, you can identify the most effective strategy while minimizing risks and improving overall campaign structure.

Aligning Marketing with Pricing Strategy

A common challenge is the disconnect between marketing and pricing decisions. Our tool synchronizes both, ensuring:

Product prices align with campaign goals
Automatic adjustments based on price changes
Identification of profitable discount and promotion opportunities

Order Optimization

Generate forward-looking, data-driven order recommendations that reduce profit losses and improve inventory efficiency — all by leveraging your already integrated pricing and marketing data, with no additional data integration required.

Sales Forecasting: Analyzes historical data — including out-of-stock periods, seasonal trends, and long-term patterns — to generate a reliable sales forecast.
Customizable Rule-Engine: Impact factors and rules are fully customizable, allowing the logic to adapt to your business needs.
Account for Future Pricing Strategies: Considers upcoming changes to your pricing strategies to optimize order volumes ahead of time.
Data-Driven Recommendations: Outputs accurate, product-level order quantity suggestions for a pre-defined time frame.

Output

All order quantity recommendations are transparent and explainable, giving you full confidence in every ordering decision on product level:

alt text

The Order Quantity recommendation is built on a robust demand forecast that factors in:

Historical sales patterns
Anticipated pricing changes
Adjustments for out-of-stock periods
Broader sales trends

From this demand forecast, we

Deduct current stock and incoming deliveries
Add expected sales until the optimization start date

The result is a granular, product-level order quantity that aligns seamlessly with your inventory processes and supports channel-specific planning.

Exploit Synergies between Ordering and Pricing

For maximum impact, combine Order Optimization with Stock-Based Pricing. This powerful synergy helps you minimize out-of-stock and overstock situations while maximizing your target KPIs — whether you're focused on revenue, profit, or turnover.

tRoas

tROAS (Target Return on Ad Spend) is a bid strategy used in digital advertising, particularly in platforms like Google Ads, where you can set a desired return on ad spend as a percentage. The algorithm then automatically adjusts bids to maximize conversion value while trying to achieve the specified return.

How tROAS Works on platforms like google:

You set a target ROAS (e.g., 400% means you want 4€ in revenue for every 1€ spent).
The algorithm adjusts bids in real-time to maximize conversion value while aiming for the target.
Higher tROAS means the algorithm prioritizes efficiency over volume, leading to fewer but more profitable conversions.
Lower tROAS means the algorithm prioritizes more conversions, even if they’re less profitable.

Marketing Option: tRoas⁻¹

Our tool uses inverted tROAS displayed as tROAS⁻¹ as Marketing Option to make marketing steering more intuitive. Instead of comparing tRoas directly (which can feel counterintuitive), the Marketing Option tRoas⁻¹ value gives you a clear sense of how aggressively you're pushing your marketing:

Lower Marketing Option tRoas⁻¹ → Less aggressive marketing
Higher Marketing Option tRoas⁻¹ → More aggressive marketing

How to Calculate it

1. tRoas to Marketing Option tRoas⁻¹

If you want to check the Marketing Option, just divide 100 by the tRoas (expressed as a whole number):

Example:

A tRoas of 1,298.70% - moderate steering

100 ÷ 12.987 = 7.7

Marketing Option tRoas⁻¹: 7.7%

A tRoas of 952.38% - more aggressive steering

100 ÷ 9.5238 = 10.5

Marketing Option tRoas⁻¹: 10.5%

This way, instead of dealing with percentage comparisons, you get a clear and simple scale to guide your decisions.

2. Marketing Option tRoas⁻¹ to tRoas

If you have a Marketing Option tRoas⁻¹ and want to find the corresponding tRoas (in percentage), simply divide the Marketing Option Float by 100.

Example:

A Marketing Option of 7.7 tRoas⁻¹ - moderate steering

100 ÷ 7.7 = 12.987 → 1,298.70%

A Marketing Option of 10.5 tRoas⁻¹ - more aggressive steering

100 ÷ 10.5 = 9.5238 → 952.38%

tRoas and Marketing Option

This table shows common tRoas values and their corresponding Marketing Option Float and Marketing Option tRoas⁻¹ for easier reference.

tRoas (%)	Marketing Option Float	Marketing Option tRoas⁻¹
10,000.00%	1.0	tROAS⁻¹: 1.0%
7,500.00%	1.3	tROAS⁻¹: 1.3%
5,000.00%	2.0	tROAS⁻¹: 2.0%
3,500.00%	2.9	tROAS⁻¹: 2.9%
2,500.00%	4.0	tROAS⁻¹: 4.0%
2,000.00%	5.0	tROAS⁻¹: 5.0%
1,500.00%	6.7	tROAS⁻¹: 6.7%
1,200.00%	8.3	tROAS⁻¹: 8.3%
1,000.00%	10.0	tROAS⁻¹: 10.0%
800.00%	12.5	tROAS⁻¹: 12.5%
600.00%	16.7	tROAS⁻¹: 16.7%
400.00%	25.0	tROAS⁻¹: 25.0%

Output Options

You have three convenient options for exporting data from our tool to your system:

A. Manually download the integration file to your computer and manually upload it into system. B. Manually upload the integration file using an API to your system C. Automatically upload the integration file using an API to your system

We always customize the data export format for each customer, so that you can decide which KPIs should be in these export files. It is also possible to export multiple files. The integration files have to be configured by the 7Learnings support team.

A. Manually download the integration file

In the Optimizations section, locate the optimization you wish to use
On the right, click the "Up-/Download" button and select the integration file you would like to download
Upload the downloaded file from your computer to your system

B. Manually Upload the integration file

In the Optimizations section, locate the optimization you wish to use
On the right, click the "Up-/Download" button and select "Create Upload" from the popup menu.
Configure the upload by specifying the following options:
- Reviewers: Assign a reviewer responsible for approving the changes before the upload. If you select yourself as a reviewer, the changes will be approved automatically
- Upload configuration: Choose the upload configurations that will be used for this upload. You can select multiple configurations to send the integration file to different locations
- Upload channels: Specify which upload channels will receive the changes. If no upload channels are selected, the changes will be sent to all available upload channels
Click "Create Upload" to finalize the process.
If you assigned the review to someone other than yourself, the upload will require additional approval from the designated reviewers.

C. Automatically upload the integration file

Please refer to the Scheduled Uploads help section.

Approving an Upload

To review the pending upload, click the "View Optimization" button (represented by the eye symbol) in the Uploads section for the relevant upload
After reviewing the changes, you can leave a comment regarding the optimization or proceed to approve and upload the changes
Once the changes are approved, they will be uploaded automatically. A double tick symbol will indicate that the upload was successful once completed

Upload Scheduling

Scheduled uploads offer a seamless way to automate your price updates, ensuring that your pricing information is always current and accurate. By establishing specific intervals for uploads, you can minimize manual intervention. Once set up, scheduled uploads will automatically create optimizations, prepare price changes for review before uploading, or, in the case of automated uploads, execute the changes immediately.

Creating a Scheduled Upload

In the Uploads section, click the "Create" button in the top left corner to start a new scheduled upload.
Configure the scheduled upload. The setup process is similar to creating a manual upload and includes the following options:
- Optimization to copy settings from: Select an existing optimization from the Optimization section to base this scheduled upload on. This will copy the selected scopes, rules, and steering targets.
- Upload frequency and schedule: Choose how often the upload should occur (daily or weekly) and specify the exact times. By clicking on the weekdays, you can easily select the days of the week when the upload should take place.
- Reviewers: Assign a reviewer responsible for approving the price changes before the upload. Alternatively, you can opt for an automated upload, which does not require manual approval.
- Automated Upload: If selected, the price changes will be uploaded immediately upon optimization creation, bypassing the need for manual approval.
- Upload configuration: Choose the upload configurations that will be used for the scheduled uploads. You can select multiple configurations to send price changes to different locations.
- Upload channels: Specify which upload channels will receive the price changes. If no upload channels are selected, the price changes will be sent to all available upload channels.
After finalizing the configuration, click the "Create Scheduled Upload" button to complete the process.

Approving and Uploading a Scheduled Upload

Note: This section is not applicable for automated uploads, which do not require approval and are uploaded immediately upon optimization creation.

After the optimization was created automatically, it must receive approval from one of the designated reviewers before any price changes can be uploaded. To review the pending price changes of a scheduled upload, click the "View Optimization" button (represented by the eye symbol).
After reviewing the price changes in the Optimization View, you can leave a comment regarding the optimization or proceed to approve and upload the changes.
Once the price changes are approved, they will be uploaded automatically. A double tick symbol will indicate that the upload was successful once completed.

Upload Evaluation

We offer several metrics that enable retrospective evaluation on our predicted sales, profit and revenue. In short, you can see if our past predictions match what occurred in reality.

The live share is the percentage of products in the optimization for which the recommended price is actually online/active. Please keep in mind that the older the optimization, the more irrelevant/outdated this share becomes, so be sure to refer to the latest optimizations if you want to know the live share.

Profit Impact

The profit impact refers to the difference between the actual (realized) profit and what the profit would have been without the optimization. This is in the context of the time period and products covered by the optimization. For example, if you uploaded an optimization 7 days ago, we calculate the actual profit generated by the products that were part of this optimization for the past 7 days and compare it to the "potential" profit these products would have generated had you not done the optimization. This "potential" profit is the one derived from the status quo point (green point in the preview curve), which just predicts the profit if you "do nothing" and keep the prices unchanged. Note that the profit metric here is calculated for all sales before returns.

Revenue Impact

The revenue impact is analogous to the profit impact, with the exception that the metric we are now measuring is the revenue.

Understanding Impact

In order to better understand how we actually calculate the impact, it's best to illustrate with an example. Let's say that two weeks ago, we have created an optimization, "X", which covers a period of two weeks and the steering strategy was "Max Profit". For this optimization, today we say that the profit impact is 2,000 EUR. In order to come up with this value, we look at two things:

The realized (actual) profit generated by the products which were part of Optimization X during these two weeks.
The predicted profit of Optimization X for the scenario where we would not have done the optimization (Status Quo or “Do Nothing”).

Let's assume that this predicted profit for “Do Nothing” is 10,000 EUR. Also, let's assume that the actual profit is 12,000 EUR. In this case, the profit impact would be 12,000 - 10,000 = 2,000 EUR. So, because we steered for Max Profit rather than doing nothing, we generated an extra 2,000 EUR, which are attributed to the steering strategy.

Please keep in mind that this impact is an incremental (relative) impact. Incremental in the sense that we always compare our tool against itself, because the “Do Nothing” scenario of the current optimization is nothing more than the “Max Profit” scenario of the previous optimization. So, the current prices (“Do Nothing”) are always the suggested prices of the previous upload (“Max Profit”). This calculation only makes sense in the context of a continuous use of the tool.

The "absolute" impact, which answers the question: "What would the profit have looked like, had we not used the tool at all?" is not shown here and is not easily quantifiable. The only reasonable way to answer this question would be to perform an A/B test. It compares results with and without the tool under similar conditions, isolating our tool's overall effect.

Sales Accuracy

The sales accuracy is of predicted sales before returns in the optimization divided by the sum of the actual sales before returns over the same period of time. For example, if we predict 100 sales before returns in the next two weeks, and in reality, only 90 sales were realized, then this value would be 90%. Values close to 100% indicate good predictability. Values above or below that indicate overprediction or underprediction respectively.

Upload Filters

When uploading optimization results to a destination—either via scheduled uploads or manual upload creation—it is possible to further refine the scope of the results. To enable this, an additional field will be available for selection during the upload creation process.

Max. Liquidation End Profit example 1

The Upload Channel Filter dropdown menu lists all combinations of identifiers defined in the Data Channels feed. Depending on how "Data Channels" is configured, the number of available combinations may vary. For more details, refer to the Initial Data Request document.

How Filters Are Defined

Filter options are created by joining all available identifiers in the project. This includes standard channel definitions such as Market = DE and Channel = Zalando. If your project utilizes Shadow Channels, these options will be extended accordingly.

What Are Shadow Channels?

Shadow Channels provide additional mapping definitions for the primary two-level identifiers (Market, Channel). They are particularly useful for replicating optimized prices to platforms with different market or channel definitions. Common uses of Shadow Channels include:

Example 1: Mapping Main Regions/Countries to Shadow Countries

Shadow Channels can abstract multiple sales countries by region. For example, suppose prices are optimized for the Polish market (Market = PL, Channel = Webshop) because it is the largest market in a region where your company operates. Instead of optimizing prices for each country, you can define Shadow Channels for related countries (e.g., CZ, BG, SK) and replicate the Polish prices, converted into local currencies, for these markets.

This setup allows you to optimize prices once for the main market-channel combination and replicate them for corresponding shadow channels, as illustrated below:

Market	Channel	Shadow Market	Shadow Channel
PL	Webshop	PL	Webshop
PL	Webshop	HR	Webshop
PL	Webshop	CZ	Webshop
PL	Webshop	EE	Webshop
PL	Webshop	HU	Webshop
PL	Webshop	LV	Webshop
PL	Webshop	LT	Webshop
PL	Webshop	BG	Webshop
PL	Webshop	SK	Webshop
PL	Webshop	SI	Webshop

Using the shadow market and channel definitions, you can filter exports to a subset of channels. For instance, you might choose to export prices only for PL, HR, and CZ, rather than all defined countries. The upload filter setup enables granular control over exports when abstraction levels exceed the project's scope definition.

Upload Filter
PL - Webshop - PL - Webshop
PL - Webshop - HR - Webshop
PL - Webshop - CZ - Webshop

Example 2: Mapping Main Regions/Countries to Integrator-Specific Keys (e.g., Tradebyte)

Shadow Channels can also function as a translation layer between regions and integrator-specific keys associated with those regions. For example, consider using Tradebyte as an integration platform for uploading to a marketplace like Zalando:

Market	Channel	Shadow Market	Shadow Channel
DE	Zalando	DE	zade
DE	Zalando	BE	zafb
DE	Zalando	BE	zafh
DE	Zalando	HR	zazfshr
DE	Zalando	CZ	zazfscz
DE	Zalando	DK	zazfsdk
DE	Zalando	EE	zazfsee
DE	Zalando	FI	zazfsfi
DE	Zalando	FR	zaff

In this example, optimized prices for the main Market = DE and Channel = Zalando are replicated to other Zalando channels in different countries. The upload filter allows you to export optimized prices for the main channel and a selected subset of subchannels directly into Tradebyte.

Upload Filter
DE - Zalando - DE - zade
DE - Zalando - BE - zafb
DE - Zalando - FR - zafr
DE - Zalando - DK - zazfsdk
DE - Zalando - FI - zazfsfi

Summary

The Upload Channel Filter feature allows to precisely control the scope of optimization results being uploaded. By leveraging standard and shadow channel definitions, exports can be filtered to specific market-channel combinations. This functionality provides flexibility to target only relevant markets or platforms, whether for manual or automated uploads.

Notes

Since export combinations are computed dynamically, the list of available options is not filtered by what the optimization contains. This means that all possible combinations defined in the data are shown, even if no products in the optimization map to those specific market-channel combinations.
Filters can be applied not only to manual uploads but can also be saved as templates for automated uploads, enabling seamless integration into recurring workflows.

Pipeline Status

You can check the status of the most recent forecast in the upper right corner next to this info page:

alt text

In progress: If the creation of your forecast is in progress, the current step of the pipeline is shown like this:

ML Models in progress now.
Success: If the forecast is successfully created, it will be displayed like this:

Successful Pipeline Run: Forecast completed 3 hours ago.
Failure: If the forecast failed we provide the step for better orientation. Below you can find more details if there is action from you required:

Data Processing failed 10 hours ago.

Failure: Explanation and what to do about it

If your pipeline failed, you can check here for more details and any required actions:

Data Import: An issue occurred while loading your data. If you do not see any specific error, we will contact you via email if any action is needed on your side.

Action: In case a specific action is requested from you in the pipeline status, please update the data accordingly. After you updated the data, please contact your Data Scientist. Once data is updated, we will rerun the pipeline, and your forecast will be available soon.
Data Processing: An issue occurred while processing your data. If you do not see any specific error, we will contact you via email if any action is needed on your side.

Action: In case a specific action is requested from you in the pipeline status, please update the data accordingly. After you updated the data, please contact your Data Scientist.
Forecast: An issue occurred during the forecast step. Your Data Scientist is reviewing the issue.

Action: No action is required from you.
Monitoring: An issue occurred during the monitoring step. Your Data Scientist is reviewing the issue.

Action: No action is required from you.
Quality Assurance: If the model's performance drops compared to the last successful forecast, the pipeline will stop, and your Data Scientist will be notified. We are reviewing and improving the models at the moment to ensure accurate forecasts. Once updated, we will rerun the pipeline, and the forecast will be available soon.

Action: No action is required from you.
Deploy Integration: An issue occurred during the integration deployment step. Your Data Scientist is reviewing the issue.

Action: No action is required from you.

Keyboard shortcuts