TrustCF: A Hybrid Collaborative Filtering Recommendation Model with Trust Information

Abstract

Recommender systems have been recognized as an effective way to deal with the information overload problem, which can recommend accurate and positive items to users from a large volume of choices. Due to its capability and simplicity, collaborative filtering (CF) is one of the most popular techniques for recommender systems. However, CF suffers from three issues which are user cold-start, item cold-start and data sparsity problems. These issues severely degrade the performance of CF. To address these issues, a hybrid collaborative filtering recommendation model, termed TrustCF, is proposed in this paper, based on user-item ratings and trust relations among users. TrustCF integrates ratings from trusted friends and similar users, ratings of similar items, item reputation and user history ratings. In particular, we modify the similarity calculation formula, considering the effect of the number of co-ratings. Trust relations among users are used to make predictions. In this way, TrustCF can alleviate the data sparsity problem and improve the recommendation performance. Experimental results on two real-world datasets verify the effectiveness of the proposed TrustCF model and show TrustCF has better recommendation accuracy than other five counterparts.