Mining User Interest Change for Improving Collaborative Filtering

Collaborative filtering recommendation system is a widely used method of providing recommendations using explicit ratings on items from users, which provides personalized recommendations on products or services to customers. However, the current research on recommendation has paid little attention to the use of time-related data in the recommendation process and the study on collaborative filtering to reflect changes in user interest. This paper proposed a methodology for mining a userpsilas time interest change in order to improve the performance of collaborative filtering recommender algorithms. The methodology consists of four phases of calculating time weight for the ratings, improving Pearsonpsilas correlation, forming neighbors, and recommendations. Empirical results show our time-incorporated collaborative filtering recommender system is significantly more accurate than a pure collaborative filtering system.