Time Series Data for different categories

I am currently helping a friend with a project. It deals with time series data of different outlets. How can I use time series forecasting with a column containing sales data and a column containing outlet ID so I can use a single model for all the outlets instead of using different model for each outlet?

I am not sure if I understand your question. If by outlet, you mean locations/shops, shouldn’t you forecast the sales for each outlet ID separately? If you do not need to forecast it separately, you can aggregate the sales across outlets (e.g. using sum) to create one time series for sales.

You can try Vector Auto Regression for multivariate output predictions

Hi, incase you want to predict for all outlets together, you can solve timeseries problem as regression problem using regression models. Do you have a date feature?

© Copyright 2013-2019 Analytics Vidhya