Recommender systems based on collaborative filtering and resource allocation

被引:27
作者
Javari A. [1 ]
Gharibshah J. [1 ]
Jalili M. [1 ,2 ]
机构
[1] Department of Computer Engineering, Sharif University of Technology, Tehran
[2] School of Electrical and Computer Engineering, RMIT University, Melbourne
关键词
Collaborative filtering; Information theory; Recommender systems; Resource allocation; Similarity; Social networks;
D O I
10.1007/s13278-014-0234-0
中图分类号
学科分类号
摘要
Recommendation systems are important part of electronic commerce, where appropriate items are recommended to potential users. The most common algorithms used for constructing recommender systems in commercial applications are collaborative filtering methods and their variants, which is mainly due to their simple implementation. In these methods, structural features of bipartite network of users and items are used and potential items are recommended to the users based on a similarity measure that shows how similar the behavior of the users is. Indeed, the performance of the memory-based CF algorithms heavily depends on the quality of similarities obtained among users/items. As the obtained similarities are more reliable, better performance for the recommender systems is expected. In this paper, we propose three models to extract reliability of similarities estimated in classic recommenders. We incorporate the obtained reliabilities to improve performance of the recommender systems. In the proposed algorithms for reliability extraction, a number of elements are taken into account including the structure of the user-item bipartite network, the individual profile of the users, i.e., how many items they have rated, and that of the items, i.e., how many users have rated them. Among the proposed methods, the method based on resource allocation provides the highest performance as compared to others. Our numerical results on two benchmark datasets (Movielens and Netflix) shows that employing resource allocation in classical recommenders significantly improves their performance. These results are of great importance since including resource allocation in the systems does not increase their computational complexity. © 2014, Springer-Verlag Wien.
引用
收藏
页码:1 / 11
页数:10
相关论文
共 51 条
[31]  
Javari A., Jalili M., Cluster-based collaborative filtering for sign prediction in social networks with positive and negative links, ACM Trans Intell Syst Technol (TIST), 5, (2014)
[32]  
Jin R., An automatic weighting scheme for collaborative filtering Sheffield, UK, pp. 337-344, (2004)
[33]  
Kleinberg J.M., Authoritative sources in a hyperlinked environment, J ACM, 46, pp. 604-632, (1999)
[34]  
Konstan J., Miller B., Maltz D., Herlocker J., Gordon L., Et al., GroupLens: applying collaborative filtering in usenet news, Commun ACM, 40, pp. 77-87, (1997)
[35]  
Koren Y., Bell R., Volinsky C., Matrix factorization techniques for recommender systems, Computer, 42, pp. 30-37, (2009)
[36]  
Liu Jian-Guo WB-HAGQ, Improved Collaborative Filtering Algorithm via Information Transformation, Int J Mod Phy C, 20, pp. 285-293, (2009)
[37]  
Lu L., Zhou T., Link prediction in complex networks: A survey, Phys A, 390, pp. 1150-1170, (2011)
[38]  
Manos Papagelis D.P., Qualitative analysis of user-based and item-based prediction algorithms for recommendation agents, Eng Appl Artif Intell, 18, pp. 781-789, (2005)
[39]  
Maslov S., Zhang Y.-C., Extracting hidden information from knowledge networks, Phys Rev Lett, 87, (2001)
[40]  
Ni J., Zhang Y.-L., Hu Z.-L., Song W.-J., Hou L., Et al., Ceiling effect of online user interests for the movies, Physica A, 402, pp. 134-140, (2014)