New Collaborative Filtering Algorithm Based on Relative Similarity
Shuhao Jiang1,2(),Liyi Zhang1,2,Zhixin Zhang2
1School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China 2Information Engineering College, Tianjin University of Commerce, Tianjin 300134, China
[Objective]The purpose of this study is to improve the overall diversity of the recommendation results. The proposed algorithm reduces errors caused by the uneven distribution and sparsity of user rating data, and then improves the recommendation accuracy and diversity. [Methods] We first generated the relative similarity index based on the number of common ratings and individual weights. Second, we modified the similarity calculation method, and the rating prediction algorithm. The proposed model improved the aggregated diversity and maintained the recommendation accuracy, which improved the marketing effects. [Results] The aggregated diversity index increased 114, the accuracy improved 6.5% on the MovieLens data compared with results generated by the traditional cosine similarity calculation, (the rating threshold was 3.5 and number of KNN is 20). [Limitations] This method was only applicable to collaborative filtering based on the nearest neighbor, and it did not include other recommendation techniques. [Conclusions] The proposed method effectively improves the diversity and accuracy of recommendation results, which significantly improves the user experience.
Adomavicius G, Kwon Y.Optimization-based Approaches for Maximizing Aggregate Recommendation Diversity[J]. Informs Journal on Computing, 2014, 26(2): 351-369.
[2]
Shambour Q, Lu J.An Effective Recommender System by Unifying User and Item Trust Information for B2B Applications[J]. Journal of Computer and System Sciences, 2015, 81(7): 1110-1126.
[3]
Yigit M, Bilgin B E, Karahoca A.Extended Topology Based Recommendation System for Unidirectional Social Networks[J]. Expert Systems with Applications, 2015, 42(7): 3653-3661.
[4]
Adomavicius G, Kwon Y.Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques[J]. IEEE Transactions on Knowledge and Data Engineering, 2012, 24(5): 896-911.
[5]
Nú?ez-Valdez E R, Lovelle J M C, Martínez O S, et al. Implicit Feedback Techniques on Recommender Systems Applied to Electronic Books[J]. Computers in Human Behavior, 2012, 28(4) 1186-1193.
[6]
Bradley K, Smyth B.Improving Recommendation Diversity [C]. In: Proceedings of the 12th Irish Conference on Artificial Intelligence and Cognitive Science. Maynooth, Ireland.2001.
[7]
Zhang M, Hurley N.Avoiding Monotony: Improving the Diversity of Recommendation Lists [C]. In: Proceedings of the 2nd ACM Conference on Recommender Systems. ACM, 2008.
[8]
Chen J, Liu Y, Hu J, et al.A Novel Framework for Improving Recommender Diversity [A]. // Behavior and Social Computing [M]. Springer International Publishing.. 2013.
[9]
Aytekin T, Karakaya M ?.Clustering-based Diversity Improvement in Top-N Recommendation[J]. Journal of Intelligent Information Systems, 2014, 42(1): 1-18.
[10]
Bobadilla J, Ortega F, Hernando A, et al.Recommender Systems Survey[J]. Knowledge Based Systems, 2013, 46: 109-132.
[11]
Lacerda A, Ziciani N.Building User Profile to Improve User Experience in Recommender Systems [C]. In: Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013.
[12]
Park Y J.The Adaptive Clustering Method for the Long Tail Problem of Recommender Systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(8): 1904-1915.
[13]
Fleder D, Hosanagar K.Blockbuster Culture’s Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity[J]. Management Science, 2009, 55(5): 697-712.