I've to build a recommendation system with a dataset where the feedback is given for the whole set of items instead to the specific items. We can see that feedback as a numerical indicator of the global happiness of the customer. I'm willing to construct a hybrid recommendation system but I don't know exactly how to exploit this global feedback.

Additionally, I've vector representations of the items.

Any idea? Thanks!


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.