0
$\begingroup$

I have time-series data with daily sales for shops and sold items. I would like to predict the number of each product sold in each store. What is the best way to solve this problem? It is necessary to avoid the situation where I manually define several thousand of models.

$\endgroup$
  • $\begingroup$ Very vague question. Show us what you have done so far and where are the issues. $\endgroup$ – user2974951 Aug 1 at 10:20
  • $\begingroup$ I read data and did exploratory data analysis and some plots. Now I think what approach should I use to predict future data, e.g. the gradient boosting algorithm or time series analysis. In the second case, I do not know if this is a good idea and whether it is feasible at all. My dataset contains about 5 million observations from 10 stores and tens of thousands of different items. The data is in a daily form for 4 years. $\endgroup$ – nukubiho Aug 1 at 10:40
  • $\begingroup$ You still need to provide more information, anyway a linear model could be used as a rough estimate. $\endgroup$ – user2974951 Aug 6 at 6:06

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.