基于双重阈值近邻查找的协同过滤算法  

Dual-Threshold Neighbors Finding Method for Neighborhood-Based Collaborative Filtering

作　　者：李颖[1] 李永丽[2] 蔡观洋[3] 

机构地区：[1]吉林师范大学计算机学院,吉林四平136000 [2]东北师范大学计算机科学与信息技术学院,长春130117 [3]吉林大学计算机科学与技术学院,长春130012

出　　处：《吉林大学学报（信息科学版）》2013年第6期647-653,共7页Journal of Jilin University（Information Science Edition）

摘　　要：为了提高协同过滤算法的推荐精度,从协同过滤算法中近邻用户/项目组的选择入手,提出基于双重阈值近邻查找的协同过滤算法。该算法能充分利用现有的稀疏用户项目评分矩阵,找出与目标用户相关性较强,且能参与到评分预测过程中的候选用户。实验结果表明,该算法相比传统的协同过滤算法及部分改进算法,其推荐精度有一定提高,对实际应用具有一定的参考价值。In order to improve the accuracy of collaborative filtering, the paper proposes a new collaborative filtering based on the dual-threshold neighbors finding method in the perspective of how to find the truly relevant user/item group. This method can take full advantage of existing sparse user-rate matrix to find some users or items which are strong relative to the active user/item, and they can participate in the progress of calculating predicate rate. The experimental results show that the recommendation accuracy of the new algorithm is better than traditional collaborative filtering and some improved algorithms.

关 键 词：协同过滤 稀疏矩阵 个性化推荐 双重阈值 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]