摘要
针对传统协同过滤算法数据稀疏性问题,提出一种基于用户和项目双向聚类的协同过滤推荐算法CFBC(Collaborative Filtering based on Bidirectional Clustering),将评分矩阵从用户和项目两个方向进行聚类,降低数据稀疏性的影响,提出一种改进的相似度计算方法P-J(Pearson-Jaccard)相关系数,提高相似度计算精度。实验证明,相较于传统协同过滤算法,该算法能有效提高推荐准确度。
Aiming at the data sparsity problem of traditional collaborative filtering algorithm,a collaborative filtering recommendation algorithm based on bidirectional clustering on users and items CFBC（Collaborative Filtering based on Bidirectional Clustering）is proposed.CFBC clusters the score matrix from two sides including users and items to decrease the influence of the data sparsity.And an improved similarity calculation method P-J（Pearson-Jaccard）correlation coefficient is presented in order to improve the accuracy of similarity calculation.Experimental results show that the proposed algorithm can effectively improve the recommendation accuracy compared with the traditional collaborative filtering algorithm.
作者
周超
孙英华
熊化峰
刘雪庆
ZHOU Chao, SUN Ying hua, XIONG Hua feng, LIU Xue qing(（College of Computer Science and Technology, Qingdao University, Qingdao 26)
出处
《青岛大学学报（自然科学版）》
CAS
2018年第1期55-60,共6页
Journal of Qingdao University(Natural Science Edition)
基金
国家自然科学基金(批准号:61502261)资助
山东省计算机网络重点实验室开放课题基金(批准号:SDKLCN-2013-07)资助
山东省高等学校科技计划项目基金(批准号:J17KB149)资助
关键词
推荐算法
协同过滤
数据稀疏性
双向聚类
P-J相关系数
recommendation algor ithm
collaborative f i l te r in g
data sparsity
bidirectional c luster ing
P-J correlation coefficient
