A Hybrid recommender System with Implicit Feedbacks in Fashion Retail

In the present paper we propose a hybrid recommender system dealing with implicit feedbacks in the domain of fashion retail. The proposed architecture is based on a collaborative-filtering module taking into account the fact that users feedbacks are not explicit scores about the items, but are obtained through user interactions with the products in terms of number of purchases; moreover, a second module provides a knowledge-based contextual post-filtering, based on both customer-oriented and business-oriented objectives. We finally present a case study where “look-oriented” recommendations have been implemented for a specific fashion retail brand.