A collaborative filtering approach to mitigate the new user cold start problem

被引:312
作者
Bobadilla, Jesus [1 ]
Ortega, Fernando [1 ]
Hernando, Antonio [1 ]
Bernal, Jesus [1 ]
机构
[1] Univ Politecn Madrid, FilmAffin Com Res Team, E-28040 Madrid, Spain
关键词
Cold start; Recommender systems; Collaborative filtering; Neural learning; Similarity measures; Leave-one-out-cross validation; RECOMMENDER;
D O I
10.1016/j.knosys.2011.07.021
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The new user cold start issue represents a serious problem in recommender systems as it can lead to the loss of new users who decide to stop using the system due to the lack of accuracy in the recommendations received in that first stage in which they have not yet cast a significant number of votes with which to feed the recommender system's collaborative filtering core. For this reason it is particularly important to design new similarity metrics which provide greater precision in the results offered to users who have cast few votes. This paper presents a new similarity measure perfected using optimization based on neural learning, which exceeds the best results obtained with current metrics. The metric has been tested on the Netflix and Movielens databases, obtaining important improvements in the measures of accuracy. precision and recall when applied to new user cold start situations. The paper includes the mathematical formalization describing how to obtain the main quality measures of a recommender system using leave-one-out cross validation. (C) 2011 Elsevier B.V. All rights reserved.
引用
收藏
页码:225 / 238
页数:14
相关论文
共 56 条
[1]   Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions [J].
Adomavicius, G ;
Tuzhilin, A .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (06) :734-749
[2]   A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem [J].
Ahn, Hyung Jun .
INFORMATION SCIENCES, 2008, 178 (01) :37-51
[3]  
[Anonymous], 2009, P 3 ACM C REC SYST A, DOI DOI 10.1145/1639714.1639720
[4]  
[Anonymous], 2007, P 2007 INT C SERV SY, DOI DOI 10.1109/ICSSSM.2007.4280214
[5]   A new collaborative filtering metric that improves the behavior of recommender systems [J].
Bobadilla, J. ;
Serradilla, F. ;
Bernal, J. .
KNOWLEDGE-BASED SYSTEMS, 2010, 23 (06) :520-528
[6]   Collaborative filtering adapted to recommender systems of e-learning [J].
Bobadilla, J. ;
Serradilla, F. ;
Hernando, A. .
KNOWLEDGE-BASED SYSTEMS, 2009, 22 (04) :261-265
[7]   Generalization of recommender systems: Collaborative filtering extended to groups of users and restricted to groups of items [J].
Bobadilla, Jesus ;
Ortega, Fernando ;
Hernando, Antonio ;
Bernal, Jesus .
EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (01) :172-186
[8]   A collaborative filtering similarity measure based on singularities [J].
Bobadilla, Jesus ;
Ortega, Fernando ;
Hernando, Antonio .
INFORMATION PROCESSING & MANAGEMENT, 2012, 48 (02) :204-217
[9]   Improving collaborative filtering recommender system results and performance using genetic algorithms [J].
Bobadilla, Jesus ;
Ortega, Fernando ;
Hernando, Antonio ;
Alcala, Javier .
KNOWLEDGE-BASED SYSTEMS, 2011, 24 (08) :1310-1316
[10]   A framework for collaborative filtering recommender systems [J].
Bobadilla, Jesus ;
Hernando, Antonio ;
Ortega, Fernando ;
Bernal, Jesus .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (12) :14609-14623