Forecast Configuration — Promotion Features

The Promotion Feature Selection screen within the Promotion Effects tab shows the various features that are available to the user. These various features can be classified according to the following categories.

  • Promotion related: Campaign Name, Offer Name, Campaign Description, Offer Type, and Offer Description.
    • Campaign Name and Offer Name contain the campaign alias and offer alias values that are assigned through the Promotion Management module; these are always selected.

    • In addition to the alias values, one or more of the following features can be enabled if they are useful: Campaign Description, Offer Description, and Offer Type. Review the data to decide which of these features will be useful.

  • Product Hierarchy: Promotion feature product hierarchy
    • Multiple levels of the product hierarchy can be selected as features to the model (for example, Class and Department). This allows the model to search for variations at each of the selected levels.

  • Location Hierarchy: Promotion feature location hierarchy
    • Multiple levels of location hierarchy can be selected as features to the model (for example, Area and Region). This allows the model to search for variations at each of the selected levels.

  • Product Attributes
    • Two attributes are supported. Select the relevant attributes that impact the promotion lift.

  • Location Attributes
    • Two attributes are supported. Select the relevant attributes that impact the promotion lift.

  • Performance Metrics: % sales on promotion, % weeks on promotion
    • In addition to the hierarchy and attributes, products can behave differently. Some products might be highly promotional compared to others. These features can be used to capture the variation lifts observed for different types of products, as determined by each performance metric.

Figure 11-31 Feature Selection for Promotion EffectsThis image shows the promotion effect forecast configuration.

For a given retailer, start with a small selection of features that you expect to have an impact on promotion lifts and add new features to see if the addition of the feature improves the model performance. The details for reviewing the model output are provided after the model settings.