A Novel Collaborative Filtering Algorithm and its Application for Recommendations in E-Commerce

With the rapid development of the Internet, the amount of data recorded on the Internet has increased dramatically. It is becoming more and more urgent to effectively obtain the specific information we need from the vast ocean of data. In this study, we propose a novel collaborative filtering algorithm for generating recommendations in e-commerce. This study has two main innovations. First, we propose a mechanism that embeds temporal behavior information to find a neighbor set in which each neighbor has a very significant impact on the current user or item. Second, we propose a novel collaborative filtering algorithm by injecting the neighbor set into probability matrix factorization. We compared the proposed method with several state-of-the-art alternatives on real datasets. The experimental results show that our proposed method outperforms the prevailing approaches.