A personalized recommendation algorithm based on conditional relative average entropy

doi:10.3969/j.issn.1000-1565.2016.04.017

Abstract

Abstract: In order to improve the accuracy of recommendation algorithm,one personalized recommendation algorithm based on conditional relative average entropy is presented.First of all,through weighted CNM algorithm we construct complex network and excavate the network’s community structure. The result is regarded as the uncertain recommendation domain. Further more,conditional mutual information and conditional relative average entropy are used to determine the effective node ordering as input of K2 algorithm,which can improve the accuracy of Bayesian network construction,and then learn Bayesian network by K2 algorithm and analyze the consumer characteristics. We use the relationship between the commodity and the consumer characteristics to confirm the recommendation domain.Finally,the empirical analysis of the actual data of the telecom operators is carried out to verify the validity of the above algorithm.

Key words: conditional relative average entropy, personality recommendation, consumer characteristics, community structure

CLC Number:

TP391

WU Liu,CHEN Meng,SHI Yongge. A personalized recommendation algorithm based on conditional relative average entropy[J]. Journal of Hebei University (Natural Science Edition), 2016, 36(4): 438-443.

References

[1] 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):16-21. DENG A L,ZHU Y Y,SHI B L.A collaborative filtering recommendation algorithm based on item rating prediction[J].Software Journal,2003,14(9):16-21.
[2] 郭艳红,邓贵仕.协同过滤系统项目冷启动的混合推荐算法[J].计算机工程,2008,34(23):11-13. GUO Y H,DENG G S.Hybrid recommendation algorithm of item cold-start in collaborative filtering system[J].Computer Engineering,2008.34(23):11-13.
[3] 谢意,陈德仁,干红华.基于浏览偏好挖掘的实时商品推荐方法[J].计算机应用,2011,31(1):89-92. DOI:10.3724/SP.J.1087.2011.00089. XIE Y,CHEN D R,GAN H H.Real-time recommendation method based on browsing preferences mining[J].Journal of Computer Application,2011,31(1):89-92.DOI:10.3724/SP.J.1087.2011.00089.
[4] 王冰怡,刘杨,聂长新,等.基于用户兴趣三维建模的个性化推荐算法[J].计算机工程,2015,41(1):65-70.DOI:10.3969/j.issn.1000-3428.2015.01.012. WANG B Y,LIU Y,NIE C X,et al.Personalized recommendation algorithm based on three-dimensional user interest modeling[J].Computer Engineering,2015,41(1):65-70.DOI:10.3969/j.issn.1000-3428.2015.01.012.
[5] LI J,ZHANG P.Mining explainable user interest from scalable user behavior data[J].Procedia Computer Science,2013,17:789-796.DOI:10.1016/j.procs.2013.05.101.
[6] 张华青,王红,滕兆明,等.多维加权社会网络中的个性化推荐算法[J].计算机应用,2011.31(9):2408-2411.DOI:10.3724/SP.J.1087.2011.02408. ZHANG H Q,WANG H,TENG Z M,et al.Personalized recommendation algorithm in multidimensional and weighted social network[J].Journal of Computer Application,2011,31(9):2408-2411.DOI:10.3724/SP.J.1087.2011.02408.
[7] 卢丹,王君博,武森.电子商务中基于复杂网络社团发现的商品推荐研究[J].工业技术创新,2015,2(1):61-65.DOI:10.14103/j.issn.2095-8412.2015.01.013. LU D,WANG J B,WU S.Research on commodity recommendation in E-commerce based on community detection in complex networks[J].Industrial Technology Innovation,2015,2(1):61-65.DOI:10.14103/j.issn.2095-8412.2015.01.013.
[8] 解?,汪小帆.复杂网络中的社团结构分析算法研究综述[J].复杂系统与复杂性科学,2005,2(3):1-12. XIE Z,WANG X F.An overview of algorithms for analyzing community structure in complex networks[J].Complex Systems and Complexity Science,2005,2(3):1-12.
[9] 张光前,白雪.基于消费性格的新商品推荐方法[J].管理科学,2015,28(2):60-68.DOI:10.3969 /j.issn.1672-0334.2015.02.006. ZHANG G Q,BAI X.Method of new commodities recommendation based on consuming personalities[J].Journal of Management Science,2015,28(2):60-68.DOI:10.3969 /j.issn.1672-0334.2015.02.006.
[10] 刘鲁蓉,孙顺根.消费心理学[M].北京:科学出版社,2007:5-9.
[11] SOTOCA J M, PLA F.Supervised feature selection by clustering using conditional mutual information-based distances[J].Pattern Recognition,2010(43):2068-2081.DOI:10.1016/j.patcog.2009.12.013.
[12] JIANG J,WANG J Y,YU H,et al.Poison identification based on Bayesian network:a novel improvement on K2 algorithm via Markov blanket[J].Advances in Swarm Intelligence,2013,7929:173-182.DOI:10.1007/978-3-642-38715-9_21.