You need an item-level explainability module and import action to use the MVLR algorithm.

To create the forecast explainability module, you need to have already created a Forecast Action list.

To create a forecast explainability module:

  1. Create a module called Module Forecast Explainability.
  2. In Pivot view:
    • Place Item_id and Forecast Feature Names as Rows dimensions.
    • Place Line Items as the Column dimension and remove Time.
    • Place the Forecast Action list in the Pages dimension (see screenshot 1 below).
    • Select OK.
  3. Add a line item called Feature Contribution.
  4. In Blueprint view, select None in the Summary column for the Feature Contribution line item.
  5. From the regular view:
    • Select Import from the Data dropdown.
  6. From the Select Source dialog:
    • Select import_action_setup_explainability.csv.
    • Click the Select button.
  7. From the File Options dialog:
    • Use the Set Default File dropdown to select Admins Only.
    • Select Next.
  8. From the Import dialog, Mapping tab:
    • Map Source to Target. The table below provides an example. Your sources and targets will vary.
SourceTarget
Column 4 FORECAST_ACTIONForecast Action
Column 1 FEATURE_NAMEList Forecast Feature Names
Column 3 ITEM_IDItem_id
(Column Headers)Forecast Explainability Line Items
    • Select Only update imported cells on the right (see screenshot 2 below).
    • Note: You don't need to map within the Item-ID or Forecast Feature name tabs. The Forecast Feature name tab will have no Target items until you run a Forecast action.
    • From the Forecast Explainability Line Items tab:
Source itemsMapped To
FEATURE_CONTRIBUTIONFeature Contribution
    • Select Run Import.
      This is how you define the import to the explainability module.
    • Optional: from Import actions, rename import_action_setup_explainability to IMP Module Forecast Explainability.

Screenshot 1: Create a new module and set dimensions.

Dialog to create a new module. It shows the dimensions to be set, Pages, Columns, and Rows.

Screenshot 2: Example of Mapping for Forecast Explainability.

Dialog of Mapping for Forecast Explainability. This shows four Sources and four Targets.

Disclaimer

We update Anapedia regularly to provide the most up-to-date instructions.