基于最近邻居聚类的协同过滤推荐算法

doi:10.3969/j.issn.0253-2778.2016.09.004

中国科学技术大学学报 ›› 2016, Vol. 46 ›› Issue (9): 736-742.DOI: 10.3969/j.issn.0253-2778.2016.09.004

• 论著 • 上一篇

基于最近邻居聚类的协同过滤推荐算法

魏慧娟，戴牡红，宁勇余

湖南大学信息科学与工程学院，湖南长沙 410082

收稿日期:2016-03-01 修回日期:2016-09-17 接受日期:2016-09-17 出版日期:2016-09-17 发布日期:2016-09-17
通讯作者: 戴牡红
作者简介:魏慧娟, 女，1990年生，硕士生. 研究方向：数据挖掘. E-mail: 1194883962@qq.com
基金资助:
湖南省自然科学基金(2015JJ2027)资助.

Collaborative filtering recommendation algorithm based on nearest neighbor clustering

WEI Huijuan, DAI Muhong, NING Yongyu

College of Information Science and Engineering , Hunan University, Changsha 410082, China

Received:2016-03-01 Revised:2016-09-17 Accepted:2016-09-17 Online:2016-09-17 Published:2016-09-17

摘要/Abstract

摘要： 随着推荐系统用户数量和服务项目增多, 可扩展性问题成为推荐算法应用的瓶颈.目前, 大部分推荐算法以及基于这些算法的改进主要集中在推荐质量上, 随着系统规模扩大, 暴露出实时推荐效率降低和运行耗时的缺点.针对这些问题, 提出了一种基于最近邻聚类的协同过滤推荐算法.首先, 该算法采用二分k-means算法把评分相似的用户划分到相同的类中, 以此建立用户聚类模型.然后, 从聚类模型中挑选出目标用户的最近邻居类作为检索空间.最后, 从检索空间中搜索目标用户的最近邻居, 由最近邻居的信息产生最终的推荐列表.实验结果表明, 该算法在保持较高的推荐质量的同时可以显著提高推荐系统的效率, 比传统的协同过滤算法可扩展性强.

关键词: 推荐系统, 系统过滤, 划分聚类, 扩展性

Abstract: With the increasing number of users and items in recommender systems, designing a scalable algorithm becomes a big challenge for recommendation systems. However, many recommendation algorithms and the improved algorithms proposed thus far have focused on improving recommendation quality, resulting in shortcomings such as lower recommendation efficiency and running time consumption as the system increases in scale. To address the problem of scalability, a collaborative filtering recommendation algorithm based on nearest neighbor clustering was proposed. Firstly, the k-means algorithm was utilized to place similar scores into the same cluster, which was used to build the user clustering model. Then, it picked out the active users’ nearest neighbor clusters from the clustering model and treats them as a retrieval space. Finally, the nearest neighbors of an active user are found according to the retrieval space, and the recommendation to the active user was given. Experimental results show that the algorithm proposed in this paper not only significantly improves the response speed of the recommendation system online but also maintains a high accuracy.

Key words: recommendation system, collaborative filtering, partition-based clustering, scalability

中图分类号:

TP311.132

魏慧娟，戴牡红，宁勇余. 基于最近邻居聚类的协同过滤推荐算法[J]. 中国科学技术大学学报, 2016, 46(9): 736-742.

WEI Huijuan, DAI Muhong, NING Yongyu. Collaborative filtering recommendation algorithm based on nearest neighbor clustering[J]. Journal of University of Science and Technology of China, 2016, 46(9): 736-742.

参考文献

［1］
ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions[J]. IEEE Transaction on Knowledge and Data Engineering, 2005, 17(6):734-749.
[2] 刘青文. 基于协同过滤的推荐算法研究[D]. 中国科学技术大学, 2013.
[3] MENG X W, HU X, WANG L C, et al. Mobile recommender systems and their applications[J]. Journal of Software, 2013, 24(1):91-108.
[4] CONSTANTINOPOULOS C, LIKAS A. Unsupervised learning of Gaussian mixtures based on variational component splitting[J]. IEEE Transactions on Neural Networks, 2007, 18(3): 745-755.
[5] CACHEDA F, CARNEIRO V, FERNNDEZ D, et al. Comparison of collaborative filtering algorithms: Limitations of current techniques and proposals for scalable, high-performance recommender systems[J]. ACM Transactions on the Web, 2011, 5(1): 161-171.
[6] NEWTON J, GREINER R. Hierarchical probabilistic relational models for collaborative filtering[C]// Proceedings of the 21st International Conference on Machine Learning—Workshop on Statistical Relational Learning. New York: ACM Press, 2004: 249-163.
[7] BELL R, KOREN Y, VOLINSKY C. Modeling relationships at multiple scales to improve accuracy of large recommender systems[C]// Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Jose: ACM Press, 2007: 95-104.
[8] DAKHEL G M, MAHDAVI M. A new collaborative filtering algorithm using K-means clustering and neighbors’ voting[C]// Proceedings of the 11th International Conference on Hybrid Intelligent Systems. Melacca, Malaysia: IEEE Press, 2011,: 179-184.
[9] FU H G, PENG J. Improved collaborative filtering algorithm based on model users [J]. Computer Engineering, 2011, 37(3):70-71,74.
[10] WEI S Y, YE N, ZHANG S, et al. Collaborative filtering recommendation algorithm based on item clustering and global similarity[C]// Proceedings of the 5th International Conference on Business Intelligence and Financial Engineering. Lanzhou, China: ACM Press, 2012: 69-72.
[11] SALAKHUTDINOV R, MNIH A, HINTON G. Restricted Boltzmann machines for collaborative filtering[C]// Proceedings of the 24th International Conference on Machine Learning. Corvallis, USA: ACM Press, 2007: 791-798.
[12] STRUNJAS S. Algorithms and models for collaborative filtering from large information corpora[D]. University of Cincinnati, USA, 2008.
[13] SHINDE S K, KULKARNI U V. Hybrid personalized recommender system using fast K-medoids clustering algorithm [J]. Journal of Advances in Information Technology, 2011, 2(3): 152-158.
[14] JIANG J, LU J, ZHANG G Q, et al. Scaling-up item-based collaborative filtering recommendation algorithm based on hadoop[J]. Computer Science Technology, 2011, 7(4): 123-126.

()
()

[1]	鲁亚男，杜东舫. 基于成对交互张量分解的标签推荐[J]. 中国科学技术大学学报, 2019, 49(1): 31-39.
[2]	方建生，许言午，蔡瑞初，秦艳. 一种基于Skill-LFM的知识点推荐方法[J]. 中国科学技术大学学报, 2018, 48(9): 755-761.
[3]	李雅美，王昌栋. 基于标签的个性化旅游推荐[J]. 中国科学技术大学学报, 2017, 47(7): 547-555.
[4]	李强，何兴盛，傅忠谦. 基于用户及物品间差异的推荐算法研究[J]. 中国科学技术大学学报, 2016, 46(2): 113-119.
[5]	郑修猛，陈福才，黄瑞阳. 基于并行化谱聚类的协同推荐算法研究[J]. 中国科学技术大学学报, 2016, 46(1): 82-86.

基于最近邻居聚类的协同过滤推荐算法

Collaborative filtering recommendation algorithm based on nearest neighbor clustering

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价