Monitor forecast accuracy

  • Article

Tip

This article describes demand forecasting functionality that's built into Microsoft Dynamics 365 Supply Chain Management. For an even better planning and forecasting experience, we recommend that you try Demand planning in Microsoft Dynamics 365 Supply Chain Management, which is Microsoft's next-generation collaborative demand planning solution. For details, see the Demand planning home page.

This article describes the types of forecast accuracy that Microsoft Dynamics 365 Supply Chain Management calculates, and explains how you can view the accuracy values.

Supply Chain Management calculates the following types of forecast accuracy:

  • Historical forecast accuracy, by comparing the historical forecast that Master Planning uses with the historical demand. To view the values (both absolute values and percentage values) for historical forecast accuracy, select Show accuracy on the Demand forecast details page.
  • The estimated accuracy of the forecasting model that is used to generate the predictions. You can view the accuracy percentage under Model details - MAPE on the Demand forecast details page.

Note

If you use the Demand forecasting Microsoft Azure Machine Learning, the calculation of internal model accuracy is based on the test data set. To specify the size of the test data set, set the TEST_SET_SIZE_PERCENT parameter on the Demand forecasting parameters page. For example, if you set the value to 20, the last 20 percent of the historical data will be used to calculate the internal model accuracy.