An Improved Collaborative Filtering Algorithm Based on Trust in E-Commerce Recommendation Systems

Collaborative filtering recommender systems have become important tools of making personalized recommendations for products or services during a live interaction nowadays. However prediction accuracy is still a big challenge for CF based recommender system. One of the reason leads to the inaccuracy comes from the neighbor selecting which only consider the similarity between users in traditional algorithms. In fact trust is also an important effective parameter in real life when people choose a choice from other friends. In this paper we suggest that the traditional emphasize on user similarity may be overstated and there are additional factors having an important role to play in guiding recommendations. Then we propose that trustworthiness of users must be an important consideration. This paper propose computational model of trust and then a predictive algorithm based on it. The experimental results proved the validity and superiority of the proposed algorithm at last.