We are currently working on improving our forecast accuracy. One of the ideas is to create a separate group of customers with low volume. While it improves the forecast, my concern is the visibility we lose at the lower level downstream. For procurement planning, we need customer level forecasts because each customer gets its own labels. Any idea on how that can work? Has anyone else used this method and how did they make it work?

From Issue: Machine Learning in Supply Chain Planning– When Art & Science Converge
(Spring 2019)

image
Answers to Your Forecasting Questions