Outlier Correction with the Intermittent Forecast Model 

Purpose

Before calculating the forecast with the intermittent forecast model, the system carries out an outlier correction.

Process

...

...

...

       1.      The system calculates the average demand from the periods that you entered. In doing so, the system considers only the periods that did not have zero demand.

On the SAP Easy Access menu under Advanced Planning and Optimization → Service Parts Planning → Planning → Forecast → Forecast Profile, you can define the number of periods on Model Parameter tab page in the Initialization Period for Intermittent Forecast Model.

       2.      The system calculates the mean absolute deviation (MAD) for these periods.

       3.      The system calculates the standard deviation as 1.25 MAD.

       4.      If the standard deviation is greater than the Parameter 1 for Outlier Correction in Intermittent Forecast Model, which you can define in the forecast profile on the Model Parameter tab page, multiplied by the average demand, the system re-calculates the average demand and the standard deviation.

       5.      During this recalculation, the system excludes those demand periods whose demand is greater than a maximum value. This value is comprised of the average demand, the standard deviation, and the Parameter 2 for Outlier Correction in Intermittent Forecast Model, which you can define in the forecast profile on the Model Parameter tab page.