# Store's unseen items sales forecasting

I am working on sales forecasting problem.I am able to provide data about which items got sold and not sold to the algorithm.How to provide algorithm information about items that are not present in the store.Is there any way we could encode this information in data or any other algorithms accepts this kind of information.Currently, I am using Neural Networks and Random Forest to forecast Sales.

• Could you explain what you mean by provide algorithm information? – c zl Sep 4 '18 at 7:45

If you use R the package forecast provides neural networks algorithm as nnetar() function and it has xreg option. You could use your stock data as regressor. Examples and details: http://pkg.robjhyndman.com/forecast/reference/nnetar.html
Or you could use var models because there is relation between stock and sales e.g. if you have low stock your sales would be min(y,stock) where y is the true demand to your products. It also applies in other direction too if you have high y then you will be out of stock fast.
But I'll suggest you to take look forecast package function nnetar() (in R).