Hello I am working on a recommendation problem in which I want to recommend the next best product to a customer. I am using a collaborative filtering approach but I would like to have as a result, the products that most influenced the recommendation. Something like " We are recommending product A because you bought B C and D".
I was doing it with implicit library but I am now exploring other approaches such as NRS.
Does anyone know if it is possible with Keras (or other frameworks) for example? Thanks