计算机应用研究2016，Vol.33Issue(3)：654-656,660,4.DOI:10.3969/j.issn.1001-3695.2016.03.003
基于聚类系数的推荐算法
Modified recommendation algorithm based on clustering coefficient
摘要
Abstract
Accordance with the problem that the mass diffusion mechanism which standard NBI algorithm used was too sim-ple,this paper proposed a modified NBI algorithm based on clustering coefficient (NBICC).This algorithm regarded recom-mendation system as a direct graph with weight.In order to obtain more accurate result,it redefined the calculation formula of similarity by considering clustering coefficient in the process of mass diffusion.Numerical results indicate that the algorithmic accuracy measured by the average ranking score,precision and recall is improved greatly.关键词
推荐系统/有向加权图/聚类系数Key words
recommendation algorithm/direct graph with weight/clustering coefficient分类
信息技术与安全科学引用本文复制引用
许鹏远,党延忠..基于聚类系数的推荐算法[J].计算机应用研究,2016,33(3):654-656,660,4.基金项目
国家自然科学基金资助项目 （）
