Create a Forecasting Profile

A forecasting profile is a collection of definitions used during the generation of demand forecasts. Each profile includes the definitions of the forecasting methods used and at what level demand data is aggregated.

Predefined Forecasting Profiles

This table lists the predefined forecasting profiles:

Forecasting Profile

Work Area

Input Measure

Output Measure

Forecasting Table

Use

Forecast Bookings

Demand Management

Demand and Supply Planning

Final Bookings History

Bookings Forecast

Forecast Bookings Definitions

For forecasting on the basis of bookings history

Forecast Bookings for Supersession Chain

Demand Management

Demand and Supply Planning

Final Bookings History

Bookings Forecast

Forecast Bookings Definitions

For forecasting on the basis of bookings history for the current item revision and latest (future) item revision in a supersession chain

Forecast Bookings Including Event Activity

Demand Management

Demand and Supply Planning

Final Bookings History

Bookings Forecast

Forecast Bookings Definitions

For forecasting on the basis of bookings history while incorporating the impact of events

Forecast Bookings Including Product Lifecycle

Demand Management

Demand and Supply Planning

Final Bookings History

Bookings Forecast

Forecast Bookings Definitions

For forecasting on the basis of bookings history and the launch date and discontinuation date

Feature-Based Bookings Forecast for New Products

Demand Management

Demand and Supply Planning

Final Bookings History

Feature Based Bookings Forecast

Feature-Based Bookings Forecast Definitions

For forecasting for new products on the basis of historical bookings and features that are used to analyze effects on product demand

Forecast Consumption

Replenishment Planning

Final Consumption History

Consumption Forecast

Forecast Consumption Definitions

For forecasting on the basis of consumption history

Forecast Shipments

Demand Management

Demand and Supply Planning

Replenishment Planning

Final Shipments History

Shipments Forecast

Forecast Shipments Definitions

For forecasting on the basis of shipments history

Forecast Shipments for Supersession Chain

Demand Management

Demand and Supply Planning

Replenishment Planning

Final Shipments History

Shipments Forecast

Forecast Shipments Definitions

For forecasting on the basis of shipments history for the current item revision and latest (future) item revision in a supersession chain

Forecast Shipments Including Event Activity

Demand Management

Demand and Supply Planning

Final Shipments History

Shipments Forecast

Forecast Shipments Definitions

For forecasting on the basis of shipments history while incorporating the impact of events

Forecast Shipments Including Product Lifecycle

Demand Management

Demand and Supply Planning

Replenishment Planning

Final Shipments History

Shipments Forecast

Forecast Shipments Definitions

For forecasting on the basis of shipments history and the launch date and discontinuation date

Feature-Based Shipments Forecast for New Products

Demand Management

Demand and Supply Planning

Final Shipments History

Feature Based Shipments Forecast

Feature-Based Shipments Forecast Definitions

For forecasting for new products on the basis of historical shipments and features that are used to analyze effects on product demand

You can't edit predefined forecasting profiles. However, you can modify copies of predefined forecasting profiles for your use.

Create a Forecasting Profile

Follow these steps to create a forecasting profile:

  1. In the Demand Management, Demand and Supply Planning, or Replenishment Planning work area, on the Tasks panel tab, under Configuration, select Manage Forecasting Profiles.

    The Manage Forecasting Profiles page opens.

  2. Click Actions > Create.

    The Manage Forecasting Profiles page opens.

  3. Enter the name and description for the forecasting profile.

  4. In Machine Learning Type, select Bayesian if you want the forecasting profile to use Bayesian machine learning for new or existing products. Bayesian machine learning uses the algorithms in Oracle Demand Management.

    Select Feature-based if you want the forecasting profile to use feature-based machine learning for new products. Feature-based machine learning uses the algorithm in the Oracle Fusion Internet of Things Intelligent Applications Cloud Service.

    Note:

    You can't select Feature-based if you want to enable your forecasting profile for the Replenishment Planning work area.

  5. In Enable in Work Area, select the check boxes for the work areas in which the forecasting profile should be available.

    After the forecasting profile is created, it'll be visible on the Managing Forecasting Profiles page in only these work areas. Moreover, during the creation of a demand plan, demand and supply plan, or replenishment plan, in the Forecast Profiles section on the Demand tab on the Plan Options page, only the forecasting profiles enabled for the work area can be selected.

  6. In Forecasting Table, select the forecasting table for the forecasting profile.

    The forecasting table defines the data aggregation levels that are used in the forecasts.

  7. In Input Measure, select the input measure for the forecasting profile.

    This measure's data is used as the basis of historical demand in forecasts.

    The measures available for selection are in the selected forecasting table and are dimensioned by time.

  8. In Output Measure, select the output measure for the forecasting profile.

    This measure stores the forecast after the plan is run.

    The measures available for selection are in the selected forecasting table and are dimensioned by time. Moreover, the available measures can't be shared across plans and are refreshed with current data.

  9. In Measure Catalogs, select the measure catalogs for the forecasting profile.

    Select all the measure catalogs that you anticipate are required for plans that use the forecasting profile. Predefined measure catalogs aren't available for selection.

  10. If your forecasting profile uses Bayesian machine learning, use the Forecasting Methods tab to configure the forecasting methods and method parameters. For more information, refer to the topic on forecasting methods for Bayesian machine learning in this chapter.

    If your forecasting profile uses feature-based machine learning, accept the default selection of the XG Boost forecasting method on the Forecasting Methods tab. For more information, refer to the topic on the forecasting method for feature-based forecasting in this chapter.

  11. If your forecasting profile uses Bayesian machine learning, use the Decomposition Groups tab to select and configure decomposition groups. For more information, refer to the topic on decomposition groups in this chapter.

    If your forecasting profile uses feature-based machine learning, use the Feature Groups tab to select and configure measures, levels, and attributes. For more information, refer to the topic on feature groups in this chapter.

  12. Use the Forecasting Parameters tab to configure forecasting parameters.

    For more information, refer to the topic on forecasting parameters for Bayesian machine learning or forecasting parameters for feature-based forecasting in this chapter.

  13. Click Save and Close.