A NOVEL FUZZY-BASED SIMILARITY MEASURE FOR COLLABORATIVE FILTERING TO ALLEVIATE THE SPARSITY PROBLEM

Abstract

Memory-based collaborative filtering is the most popular approach to build recommender systems. Despite its success in many applications, it still suffers from several major limitations, including data sparsity. Sparse data affect the quality of the user similarity measurement and consequently the quality of the recommender system. In this paper, we propose a novel user similarity measure based on fuzzy set theory along with default voting technique aimed to provide a valid similarity measurement between users wherever the available ratings are relatively rare. The main idea of this research is to model the rating behaviour of each user by a fuzzy set, and use this model to determine the user's degree of interest on items. Experimental results on the MovieLens and Netflix datasets show the effectiveness of the proposed algorithm in handling data sparsity problem. It also outperforms some state-of-the-art collaborative filtering algorithms in terms of prediction quality.