基于加权Slope One填充的协同聚类推荐算法  

Co-Clustering Recommendation Algorithm Based on Weighted Slope One Filling

作　　者：陈嘉超 卢敏[1] 丁伟健 陈志辉 CHEN Jiachao;LU Min;DING Weijian;CHEN Zhihui(College of Science,Jiangxi University of Science and Technology,Ganzhou 341000,China;College of Information Science and Engineering,Jiaxing University,Jiaxing 314001,China)

机构地区：[1]江西理工大学理学院,江西赣州341000 [2]嘉兴学院信息科学与工程学院,浙江嘉兴314001

出　　处：《现代信息科技》2023年第22期73-77,82,共6页Modern Information Technology

摘　　要：针对传统协同过滤算法数据集稀疏性高、推荐性能差的问题,提出一种基于K-means聚类与加权Slope One填充的协同过滤推荐算法。首先以用户特征为聚类依据,聚类生成K个用户集群,其次通过加权SlopeOne算法预测并填充每个集群内部的评分矩阵,最后合并各类别的评分矩阵,设计融合Baseline算法和基于物品协同过滤算法的混合算法预测用户评分。在MovieLens数据集上进行新算法与其他算法的对比实验,实验结果表明,该算法能有效缓解数据稀疏性,提高预测精度。To solve the problem of high sparsity and poor recommendation performance of traditional collaborative filtering algorithms,a collaborative filtering recommendation algorithm based on K-means clustering and weighted Slope One filling is proposed.Firstly,K clusters of users are clustered based on user characteristics,secondly,the rating matrix within each cluster is predicted and populated by the weighted Slope One algorithm,and finally,the rating matrix of each category is merged and a hybrid algorithm combining Baseline algorithm and item-based collaborative filtering algorithm is designed to predict user ratings.The new algorithm was compared with other algorithms on the MovieLens dataset,and the experimental results showed that the algorithm can effectively alleviate data sparsity and improve prediction accuracy.

关 键 词：协同过滤 用户聚类 评分预测 个性化推荐 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]