I have data of 2000 stores with associated 145 features(example: ambience, holidays, no. of brands) and their monthly sales for 2 years. It means that for every store I have sales data and other features for 24 months. I have to forecast sales for every store on a monthly basis. I have basic idea of LSTM but here its like 2000 time series with 145 features with just 24 data points or in other words for one time step, I have 2000 series with 145 features. what is the best approach to model so that I dont have to build model separately for each store.
Asked
Active
Viewed 43 times
0
-
https://stats.stackexchange.com/questions/344705/product-demand-forecasting-for-thousands-of-products-across-multiple-stores/344813#344813 – Skander H. Jun 17 '20 at 08:47
-
https://stats.stackexchange.com/questions/380599/is-it-possible-to-automate-time-series-forecasting/380689#380689 – Skander H. Jun 17 '20 at 08:47