点击次数：

论文类型：会议论文

发表时间：2007-09-05

收录刊物：EI

摘要：Collaborative filtering recommender systems have become important tools of making personalized recommendations for products or services in E-commerce nowadays. In fact, case-based reasoning has some natural similarity with collaborative filtering from the view of recognizing science. This paper proposes a novel idea of combing CBR and CF algorithm together to improve the performance of recommender systems. For another, a social trust model is advanced in the recommendation steps to improve the prediction accuracy. Experimental results show that using case-based reasoning and social trust have better prediction results and solve the sparsity problem of recommender systems from certain angle. ©2007 IEEE.