期刊名称：International Journal of Hybrid Information Technology
印刷版ISSN：1738-9968
出版年度：2016
卷号：9
期号：4
页码：437-446
DOI：10.14257/ijhit.2016.9.4.38
出版社：SERSC
摘要：Collaborative filtering is the most successful and widely used technology in E-commerce recommendation system. However, the traditional collaborative filtering recommendation algorithm faces severe problems of sparse user ratings and poor scala- bility. Slope One algorithm can reduce the sparsity of ratings, improve the recommenda- tion accuracy, but with the growth of users and items, the running time increases rapidly. In this paper, we first introduce the feature similarity into Slope One algorithm, then com- bine it with ants clustering algorithm, thus reliving the influence of rating sparsity, im- proving the searching speed, and reducing the searching costs. Experimental results show that the new algorithm can efficiently improve recommendation quality.
