on 2023 May 08 3:56 PM
Hello,
the link on the SAP help page shows when the corresponding error measure is useful.
One advantage of IBP is that it can automatically determine the best forecast. to do this, I build a profile with various forecast algorithms and have the best algorithm selected according to an error measure.
But how can I understand the note on the SAP page? I have planning objects that have a forecast erorr for optimising the forecast for average demand (i.e. MAPE , MPE) and other seasonality and therefore need MASE or MAP.
I can only select the best forecast model according to an error measure, which may then have been calculated with a "not so suitable" error measure.
Request clarification before answering.
Hi Oliver,
the help page is meant to help you understand how the different error measures works. Of course there is no "one size fit all" when it comes to algorithms and error measures.
If you feel that separating planning objects with seasonality from planning objects without seasonality is important in terms of error measures, then I suggest you forecast these separately (using the Time Series Analysis and a corresponding planning filter) with two different forecast models. So you can use different best fit models for the seasonal planning objects and for the not seasonal ones.
Best regards
Laura
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hi Oliver,
yes you can store the result of the time series analysis in attributes and use it for the planning filter. Here you can find some more information: https://help.sap.com/docs/SAP_INTEGRATED_BUSINESS_PLANNING/feae3cea3cc549aaa9d9de7d363a83e6/0827673a...
User | Count |
---|---|
10 | |
5 | |
4 | |
4 | |
3 | |
2 | |
2 | |
1 | |
1 | |
1 |
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.