In retail demand forecasting, we often resort to aggregating data across product or location hierarchies to obtain more accurate forecasts.

I understand the concept intuitively: You have a better chance of figuring out how many sweaters overall you will sell in all your stores next week than you do of figuring out how many size XS Purple Sweaters you are going to sell next week at your Atlanta store.

But I'm wondering if there is a more solid theoretical mathematical grounding for this idea, or if this is just an intuitive add hoc assumption that is used by forecasters?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.