集成项目类别与语境信息的协同过滤推荐算法  

Collaborative filtering recommender algorithm for integrating item category and contextual information

作　　者：姚忠[1] 吴跃[1] 常娜[2] 

机构地区：[1]北京航空航天大学经济管理学院,北京100083 [2]国家信息中心,北京100045

出　　处：《计算机集成制造系统》2008年第7期1449-1456,共8页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(70401001)~~

摘　　要：为改进基于项目的协同过滤推荐算法的推荐效果,在项目相似性计算时引入项目类别因素的影响,得出新的推荐算法,即基于项目类别的修正条件概率相似性,并在此基础上提出集成语境信息的多维推荐模型。通过与相关相似性、余弦相似性和修正余弦相似性的数值实验对比,证明在数据比较稀疏的情况下,改进算法所获得的推荐效果有较大提高。To improve recommendation result of the item-based collaborative filtering algorithm, influence of product category in product similarity computation was introduced, and a new recommendation algorithm, i. e. Categorybased Adjusted Conditional Probability similarity （CACP）, was proposed. Base on this algorithm, multi-dimension recommendation model for integrated contextual information was also presented. Experiment was conducted to com- pare correlation similarity, cosine similarity and adjusted cosine similarity. Results showed that recommendation result of CACP was greatly improved especially in sparse data environment.

关 键 词：电子商务推荐系统 协同过滤 项目相似性 项目类别 语境信息 条件概率 数据稀疏性 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]