on 09-17-2015 10:39 AM
Hi All,
When I see books like springers I understand that it is always better to forecast demand at a aggregated level say Product-Location level and disaggregate at a lower level as required rather than forecasting at a detailed level. This would give better forecasting results.
I wanted to confirm whether the above understanding is correct. Also is there any thumb rule to achieve the right level of aggregation for better forecasting.
Thank you.
Lakshmanamurthy,
Your first have to define what you mean by 'better'. No, it is not necessarily 'better' to forecast at an aggregated level. Like everything else in business, there are advantages and disadvantages to forecasting at a high level or at a detailed level.
Performing a statistical forecast (e.g. using mathematical models) at an aggregated level will typically take less hardware and will usually run more quickly. That doesn't mean that the resulting forecast will be the best 'fit' to meet the client's business requirements.
In the end, it depends upon the business requirements. Speak to the client. The actual forecasting business cycle will determine the best level at which to forecast. There is no fixed rule.
Best Regards,
DB49
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
User | Count |
---|---|
8 | |
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.