AI Foundation Cloud Services and Forecasting

Each AI Foundation application has parameters that are specific to the batch processing, data movement, algorithms, and user interfaces of those modules. These configurations are stored in several database tables available through the Control & Tactical Center. If you are implementing any AI Foundation applications as part of your project, review the Retail AI Foundation Cloud Services Implementation Guide.

If you are implementing any planning application (Merchandise Financial Planning, IPOCS-Demand Forecasting, or Assortment Planning), then you are required to configure and use the Forecasting module in the AI Foundation application interface. This requires initial configurations to select forecast parameters, as well as post-data load configurations to select forecast data levels and perform testing of the chosen algorithm. For basic information about Forecasting and what the AI Foundation application functionality can support, refer to the “Manage Forecast Configurations” section in the AI Foundation User Guide.

To configure the forecast process for Planning, use the Manage System Configurations screen in the Control Center to review and modify the configurations in RSE_CONFIG. These values can be set up now, but you cannot complete the rest of the forecasting process until your foundation data has been loaded into AI Foundation.

Appl Code	Parameter Name	Description
RSE	LOAD_EXTENDED_PROD_HIER	Y or N value (default value is Y). Extended hierarchy refers to a 9-level structure with style and style/color as extra levels above SKU. This is used only for specific applications such as AP, IPO, and LPO. If you are not using one of the listed applications or you don’t have styles and style/colors, then you can ignore this parameter (the extended hierarchy won’t be used even if generated).
RSE	EXTENDED_HIERARCHY_SRC	Value can be set as either RMS or NON-RMS. Default value is NON-RMS. If using RMFCS or RMS-sourced data, or you are loading RAP with data in RMS-like format, change this value to RMS. Data loaded using the RAP foundation CSV files can be provided in either an RMS or non-RMS format, but RMS format is preferred (as detailed later in this document for the PRODUCT.csv file). All interface samples use RMS-formatted data, so change this parameter to RMS if you are following those guidelines.
PMO	PMO_PROD_HIER_TYPE	The hierarchy ID to use for the Lifecycle Pricing Optimization product and the Forecasting module. AIF applications have 2 product hierarchies: 1 = Basic 7-level hierarchy without styles or colors 3 = Extended 9-level hierarchy with style/color Default value is 3. If the extended hierarchy is enabled and you are using one of the apps listed above on LOAD_EXTENDED_PROD_HIER, keep this value as 3. If you are not using the extended hierarchy (such as for MFP-only implementations), change this value to 1.
RSE	PROD_HIER_SLSTXN_HIER_LEVEL_ID	This parameter identifies the extended hierarchy level at which sales transactions are provided (7-Style, 8-Style/color or 9-Style/color/Size). It MUST match the extended hierarchy leaf level. Default value is 9. If you are not using the extended hierarchy then ignore this parameter, it will not be used.
PMO	PMO_AGGR_INVENTORY_DATA_FLG	Specifies whether inventory data is present and if it should be used when aggregating activities data for LPO and forecasting (only some forecast types use inventory). Set this value to N if inventory data is not loaded or not needed for forecasting (inventory data is not used for MFP forecasting but it is required for other applications like Lifecycle Pricing Optimization and Inventory Planning Optimization). Default value is Y.