期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2007
卷号：7
期号：7
页码：134-138
出版社：International Journal of Computer Science and Network Security
摘要：Collaborative filtering is one of the most frequently used techniques in personalized recommendation systems. But currently used user-based collaborative filtering recommendation algorithm and the collaborative filtering recommendation algorithm based on item rating prediction has disadvantage in similarity computation method. Basing on this disadvantage, the paper puts forward an improved collaborative filtering recommendation algorithm. We improve it in two aspects: First, we bring in a coefficient to coordinate the problem of inexact finding and falling recommendation quality which is caused by the fewer items when weighting the user similarity. Second, we collect the users�� interest words implicitly when build the user interest model. At last, we develop an online network bookshop as an example, test and analyze the three algorithms. The testing results show that in most cases, the improved algorithm that we put forward can improve recommendation quality.
关键词：Collaborative Filtering; Personalized Recommendation Algorithm; Mean Absolute Error
