摘要
协同过滤算法中用户相似性度量的准确性对推荐质量有显著影响。为了提高用户协同过滤算法中近邻选择的准确率,提出一种加权的皮尔逊相关系数(PCC),可根据用户-项目的评分数,直接计算出PCC加权因子。将改进的皮尔逊相似度机制用于Movie Lens,Douban和Epinions数据集进行实证分析。结果表明,提出的算法可以有效提高协同过滤推荐的平均绝对误差(MAE)和准确度。
The similarity measure between users has significant impact on the results of collaborative filtering recommendationsystem. To increase the accuracy of neighbor selection, a weighted Pearson Correlation Coefficient(PCC)similaritymeasurement is proposed to calculate PCC weighting factor directly with the number of user-item ratings. The improvedpearson similarity metrics is applied to empirical analysis of the MovieLens, Douban and Epinions dataset. Experimentalresults show that the proposed method can improve the recommendation accuracy of collaborative filtering effectively interms of Mean Absolute Error(MAE)and precision.
作者
范永全
杜亚军
FAN Yongquan;DU Yajun(School of Computer & Software Engineering, Xihua University, Chengdu 610039, China)
出处
《计算机工程与应用》
CSCD
北大核心
2016年第22期222-225,259,共5页
Computer Engineering and Applications
基金
教育部春晖计划(No.Z2011088)
四川省教育厅重点项目(No.11ZB002)
四川省高校重点实验室基金(No.SZJJ2012-027
No.SZJJ2014-033)
西华大学重点科研基金项目(No.Z1412620)