Please wait a minute...
Advanced Search
现代图书情报技术  2015, Vol. 31 Issue (6): 27-32    DOI: 10.11925/infotech.1003-3513.2015.06.05
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于项目评分预测的混合式协同过滤推荐
盈艳, 曹妍, 牟向伟
大连海事大学交通运输管理学院 大连 116000
A Hybrid Collaborative Filtering Recommender Based on Item Rating Prediction
Ying Yan, Cao Yan, Mu Xiangwei
Transportation Management College, Dalian Maritime University, Dalian 116000, China
全文: PDF(521 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

目的】改进传统协同过滤推荐算法以缓解其存在的数据稀疏性问题, 进而提高评分预测的精度。【方法】提出整合K-means聚类和Slope One算法的混合式协同过滤推荐框架和KSUBCF算法。利用基于K-means聚类的Slope One算法预测填充矩阵中必要的未评分项, 利用基于用户的协同过滤推荐算法实现推荐。【结果】实验结果表明, 随着邻居数目的增加, 该算法比原Slope One算法在MAE(平均绝对误差)值上有8.8%-21%的下降, RMSE(均方根误差)值有17%-28.1%的下降。【局限】该算法仍然依赖用户-项目评分数据矩阵。【结论】该算法与其他传统协同过滤算法相比, MAE值分别有10%和43.8%的下降, RMSE值也有20.1%和37.4%的下降, 说明本文方法可以提高预测精度。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
盈艳
曹妍
牟向伟
关键词 混合式协同过滤项目评分Slope One预测MAE    
Abstract

[Objective] By improving the traditional collaborative filtering recommendation algorithm to alleviate the existing data sparseness problem, thus enhance the prediction precision. [Methods] This paper proposes a hybrid collaborative filtering recommender framework and KSUBCF algorithm integrated K-means clustering and Slope One algorithm. Firstly, this algorithm uses the Slope One algorithm based on K-means clustering to predict item default rating. And then, to implement recommendation by the collaborative filtering recommendation algorithm based on users. [Results] The experimental results show that with the increase of neighbors numbers, this algorithm is better than the original Slope One algorithm, which MAE value is reduced by 8.8% to 21% and RMSE value is reduced by 17% to 28.1%. [Limitations] This algorithm still relies on user-project score data matrix. [Conclusions] Compared with other traditional collaborative filtering algorithms, the decreases of the MAE value are 10% and 43.8% respectively and the decreases of the RMSE value are 20.1% and 37.4%. The proposed method can improve the prediction precision.

Key wordsHybrid collaborative filtering    Item rating    Slope One prediction    MAE
收稿日期: 2014-12-12     
:  G202  
基金资助:

本文系中国博士后科学基金资助项目“大数据环境下散杂货多式联运领域知识发现方法研究”(项目编号:2014M551063)、省社科联2014年度辽宁经济社会发展立项课题“辽宁冷链物流产业建设与发展研究”(项目编号:2014lslktzdian-11)和辽宁省教育厅科学技术研究项目“大数据环境下散杂货多式联运综合领域知识的表达与共享”(项目编号:L2014203)的研究成果之一。

通讯作者: 曹妍, ORCID: 0000-0002-8383-083X, E-mail: caoyan@dlmu.edu.cn。     E-mail: caoyan@dlmu.edu.cn
作者简介: 作者贡献声明: 曹妍: 提出研究方向, 设计研究方法; 盈艳: 设计算法, 实验及分析, 论文撰写; 牟向伟: 收集数据, 论文修订。
引用本文:   
盈艳, 曹妍, 牟向伟. 基于项目评分预测的混合式协同过滤推荐[J]. 现代图书情报技术, 2015, 31(6): 27-32.
Ying Yan, Cao Yan, Mu Xiangwei. A Hybrid Collaborative Filtering Recommender Based on Item Rating Prediction. New Technology of Library and Information Service, DOI:10.11925/infotech.1003-3513.2015.06.05.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2015.06.05

[1] 李聪, 梁昌勇, 杨善林. 电子商务协同过滤稀疏性研究: 一个分类视角[J]. 管理工程学报, 2011, 25(1): 94-101. (Li Cong, Liang Changyong, Yang Shanlin. Sparsity Problem in Collaborative Filtering: A Classification [J]. Journal of Industrial Engineering and Engineering Management, 2011, 25(1): 94-101.)
[2] Huang Z, Chen H, Zeng D. Applying Associative Retrieval Techniques to Alleviate the Sparsity Problem in Collaborative Filtering [J]. ACM Transactions on Information Systems, 2004, 22(1): 116-142.
[3] 王洋, 骆力明. 一种解决协同过滤数据稀疏性问题的方法[J]. 首都师范大学学报: 自然科学版, 2012, 33(4): 1-5, 26. (Wang Yang, Luo Liming. In Collaborative Filtering a Method of Alleviating the Sparsity Problem [J]. Journal of Capital Normal University: Natural Science Edition, 2012, 33(4): 1-5,26.)
[4] Zhang J Y, Pu P. A Recursive Prediction Algorithm for Collaborative Filtering Recommender Systems [C]. In: Proceedings of the 2007 ACM Conference on Recommender systems, Minneapolis, MN, USA. 2007: 57-64.
[5] 林德军. 基于Slope One改进算法推荐模型的设计与实现[D]. 北京: 北京邮电大学, 2012. (Lin Dejun. Design and Realization of the Recommendation Model Based on the Slope One Improved Algorithm [D]. Beijing: Beijing University of Posts and Telecommunications, 2012.)
[6] 邓爱林, 朱扬勇, 施伯乐. 基于项目评分预测的协同过滤推荐算法[J]. 软件学报, 2003, 14(9): 1621-1628. (Deng Ailin, Zhu Yangyong, Shi Baile. A Collaborative Filtering Recommendation Algorithm Based on Item Rating Prediction [J]. Journal of Software, 2003, 14(9): 1621-1628.)
[7] 王鹏, 王晶晶, 俞能海. 基于核方法的User-Based协同过滤推荐算法[J]. 计算机研究与发展, 2013, 50(7): 1444-1451. (Wang Peng, Wang Jingjing, Yu Nenghai. A Kernel and User-Based Collaborative Filtering Recommen­dation Algorithm [J]. Journal of Computer Research and Development, 2013, 50(7): 1444-1451.)
[8] Ma H, King I, Lyu M R. Effective Missing Data Prediction for Collaborative Filtering [C]. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2007: 39-46.
[9] Lemire D, Maclachlan A. Slope One Predictors for Online Rating-Based Collaborative Filtering [C]. In: Proceedings of the 2005 SIAM International Conference on Data Mining (SDM'05), Newport Beach,California, USA. 2005.
[10] 孙丽梅, 李晶皎, 孙焕良. 基于动态k近邻的SlopeOne协同过滤推荐算法[J]. 计算机科学与探索, 2011, 5(9): 857-864. (Sun Limei, Li Jingjiao, Sun Huanliang. SlopeOne Collaborative Filtering Recommendation Algorithm Based on Dynamic k-Nearest-Neighborhood [J]. Journal of Frontiers of Computer Science and Technology, 2011, 5(9): 857-864.)
[11] Zhang D J. An Item-based Collaborative Filtering Recommendation Algorithm Using Slope One Scheme Smoothing [C]. In: Proceedings of the 2nd International Symposium on Electronic Commerce and Security, Nanchang, China. IEEE, 2009: 215-217.
[12] Wang P, Ye H W. A Personalized Recommendation Algorithm Combining Slope One Scheme and User Based Collaborative Filtering [C]. In: Proceedings of the 2009 International Conference on Industrial and Information Systems, Haikou, China. IEEE, 2009: 152-154.
[13] 肖敏. 基于领域本体的电子商务推荐技术研究[D]. 武汉: 武汉理工大学, 2009. (Xiao Min. Research on Electronic Commerence Recommendation Technology Based on Domain Ontology [D]. Wuhan: Wuhan University of Technology, 2009.)
[14] Chen Y J, Chu H C, Chen Y M, et al. Adapting Domain Ontology for Personalized Knowledge Search and Recommendation [J]. Information & Management, 2013, 50(6): 285-303.
[15] Cheng S T, Chou C L, Horng G J. The Adaptive Ontology- based Personalized Recommender System [J]. Wireless Personal Communications, 2013, 72(4): 1801-1826.

[1] 宋梅青. 面向协同过滤推荐的多粒度用户偏好挖掘研究[J]. 现代图书情报技术, 2015, 31(12): 28-33.
[2] 王忠群, 乐元, 修宇, 皇苏斌, 汪千松. 基于模板用户信息搜索行为和统计分析的共谋销量欺诈识别[J]. 现代图书情报技术, 2015, 31(11): 41-50.
[3] 何跃, 宋灵犀, 齐丽云. 负面事件中的品牌网络口碑溢出效应研究——以“圆通夺命快递”事件为例[J]. 现代图书情报技术, 2015, 31(10): 58-64.
[4] 张李义, 张皎. 一种基于主成分分析和随机森林的刷客识别方法[J]. 现代图书情报技术, 2015, 31(10): 65-71.
[5] 王忠群, 皇苏斌, 修宇, 张义. 基于领域专家和商品特征概念树的在线商品评论深刻性度量[J]. 现代图书情报技术, 2015, 31(9): 17-25.
[6] 赵静娴. 基于决策树的网络伪舆情识别研究[J]. 现代图书情报技术, 2015, 31(6): 78-84.
[7] 伍杰华, 朱岸青. 混合拓扑因子的科研网络合作关系预测[J]. 现代图书情报技术, 2015, 31(4): 65-71.
[8] 李胜, 王叶茂. 一种基于本体和位置感知的图书馆书籍推荐模型[J]. 现代图书情报技术, 2015, 31(3): 58-66.
[9] 陈涛, 张永娟, 陈恒. Web数据到RDF数据的框架实现[J]. 现代图书情报技术, 2015, 31(2): 1-6.
[10] 王伟军, 宋梅青. 一种面向用户偏好定向挖掘的协同过滤个性化推荐算法[J]. 现代图书情报技术, 2014, 30(6): 25-32.
[11] 吴珊燕, 许鑫. 基于案例推理的菜谱推荐系统研究[J]. 现代图书情报技术, 2013, (12): 34-41.
[12] 刘勘, 朱怀萍, 刘秀芹. 基于支持向量机的网络伪舆情识别研究[J]. 现代图书情报技术, 2013, 29(11): 75-80.
[13] 熊涛, 何跃. 微博转发网络中意见领袖的识别与分析[J]. 现代图书情报技术, 2013, (6): 55-62.
[14] 李树青, 王建强. 一种结合借阅时间特征分析的读者兴趣可视化识别方法[J]. 现代图书情报技术, 2013, (5): 46-53.
[15] 寇继虹, 戴亦舒, 刘芳, 吴珺, 徐承欢, 曹倩. 动态思维导图软件TheBrain的功能机制分析[J]. 现代图书情报技术, 2012, (12): 45-51.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn