on 10-09-2007 4:11 AM
Dear All,
I have a query in Demand Planning in SCM 4.1.
I have a seasonal effect in my sales data. However the seasonal period can move by about 2 weeks. say i had a festival starting in first week of December last year, this year it is going to start in 3rd week. How do I use the forecasting techniques to model this shift behavior. In my forecast I expect the values to peak from 3 week of December, this year.
Regards,
Kedar
Try also the "Length variation" field in Control Parameters in Forecast Profile. It might help for optimization of seasonal length.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
You may have to explore event based planning for better results.
the other option is to backup the seasonal coefficients generated through DP run and edit them based on additional information. Using the information, you can reengineer the forecasts.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hi Kedar.
I would suggest that the fact that there is movement in the festival dates means that it cannot be seen as seasonal (at least at the level of detail you are talking about)
Have you thought about using MLR using the festivals as a causal factor?
Regards, Mark.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
User | Count |
---|---|
7 | |
4 | |
3 | |
2 | |
2 | |
1 | |
1 | |
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.