An Evidential Collaborative Filtering Dealing with Sparsity Problem and Data Imperfections

Abstract

One of the most promising approaches commonly used in Recommender Systems (RSs) is Collaborative Filtering (CF). It relies on a matrix of user-item ratings and makes use of past users’ ratings to generate predictions. Nonetheless, a large amount of ratings in the typical user-item matrix may be unavailable. The insufficiency of available rating data is referred to as the sparsity problem, one of the major issues that limit the quality of recommendations and the applicability of CF. Generally, the final predictions are represented as a certain rating score. This does not reflect the reality which is related to uncertainty and imprecision by nature. Dealing with data imperfections is another fundamental challenge in RSs allowing more reliable and intelligible predictions. Thereupon, we propose in this paper a Collaborative Filtering system that not only tackles the sparsity problem but also deals with data imperfections using the belief function theory.