I was trying to forecast the truck numbers required at each distribution location...for that I was forecasting the shipments(number of units) at each location and dividing it by a factor to get the truck load...

Currently I was considering only the shipments but I thought it would be better to include open sales orders as an additional variable in the existing time series data... So for this which statistical model available to consider.. Will Arimax or Sarimax work?

Forecast periods will be 7 days in week.. please suggest how to approach this problem using traditional statistical forecasting methods.

Thank you

  • $\begingroup$ I think there is something like Gaussian Processes for multiple target variables. I have played around with this in order to predict exchange rates between different currencies (where the target variables depend on each other)... You could check arxiv.org/abs/2002.03471 $\endgroup$ – Fabian Werner Jan 22 at 11:01
  • $\begingroup$ If you were using (S)ARIMA until now (without the additional variable), SARIMA(X) is a natural extension. $\endgroup$ – Richard Hardy Jan 22 at 11:03

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.