Arthur F. da Costa
Marcelo G. Manzato
ABSTRACT
Recommender systems were created to represent user preferences for the purpose of suggesting items to purchase or examine. However, there are several optimizations to be made in these systems mainly with respect to modeling the user profile and remove the noise information. This paper proposes a collaborative filtering approach based on preferences of groups of users to improve the accuracy of recommendation, where the distance among users is computed using multiple types of users' feedback. The advantage of this approach is that relevant items will be suggested based only on the subjects of interest of each group of users. Using this technique, we use a state-of-art collaborative filtering algorithm to generate a personalized ranking of items according to the preferences of an individual within each cluster. The experimental results show that the proposed technique has a higher precision than the traditional models without clustering.
- M. B.-R. F. T. A. Adomavicius, G. Context-aware recommender systems. AI Magazine, pages 67--80, 2011.Google Scholar
Cross Ref
- J. S. Breese, D. Heckerman, and C. Kadie. Empirical analysis of predictive algorithms for collaborative filtering. In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, UAI'98, pages 43--52, San Francisco, CA, USA, 1998. Morgan Kaufmann Publishers Inc. Google ScholarDigital Library
- I. Cantador, P. Brusilovsky, and T. Kuflik. 2nd workshop on information heterogeneity and fusion in recommender systems (hetrec 2011). In Proceedings of the 5th ACM conference on Recommender systems, RecSys 2011, New York, NY, USA, 2011. ACM.Google Scholar
- A. da Costa Fortes and M. G. Manzato. Ensemble learning in recommender systems: Combining multiple user interactions for ranking personalization. In Proceedings of the 20th Brazilian Symposium on Multimedia and the Web, WebMedia '14, pages 47--54, New York, NY, USA, 2014. ACM. Google ScholarDigital Library
- A. da Silveira Dias, L. K. Wives, and V. Roesler. Enhancing the accuracy of ratings predictions of video recommender system by segments of interest. In 19th Brazilian Symposium on Multimedia and the Web, WebMedia '13, Salvador, Brazil, November 5--8, 2013, pages 241--248, 2013. Google ScholarDigital Library
- J. Han, M. Kamber, and A. K. H. Tung. Spatial clustering methods in data mining: A survey. In H. J. Miller and J. Han, editors, Geographic Data Mining and Knowledge Discovery, Research Monographs in GIS. Taylor and Francis, 2001.Google Scholar
- T.-H. Kim, Y.-S. Ryu, S.-I. Park, and S.-B. Yang. An improved recommendation algorithm in collaborative filtering. In Proceedings of the Third International Conference on E-Commerce and Web Technologies, EC-WEB '02, pages 254--261, London, UK, UK, 2002. Springer-Verlag. Google ScholarDigital Library
- Y. Koren. Factor in the neighbors: Scalable and accurate collaborative filtering. ACM Transactions on Knowledge Discovery from Data (TKDD), 4(1):1--24, Jan. 2010. Google ScholarDigital Library
- W. Li and W. He. An improved collaborative filtering approach based on user ranking and item clustering. In M. Pathan, G. Wei, and G. Fortino, editors, Internet and Distributed Computing Systems, volume 8223 of Lecture Notes in Computer Science, pages 134--144. Springer, 2013. Google ScholarDigital Library
- J. MacQueen. Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics, pages 281--297, Berkeley, Calif., 1967. University of California Press.Google Scholar
- T. M. Mitchell. Machine Learning. McGraw-Hill, Inc., New York, NY, USA, 1 edition, 1997. Google ScholarDigital Library
- J.-S. L. Park, Hae-Sang and C.-H. Jun. A k-means-like algorithm for k-medoids clustering and its performance. Proceedings of ICCIE (2006), pages 102--117, 2006.Google Scholar
- F. R., L. R., and B. S. Introduction to recommender systems handbook. In Recommender Systems Handbook, pages 1--35. Springer US, 2011.Google ScholarCross Ref
- S. Rendle. Factorization machines with libFM. ACM Trans. Intell. Syst. Technol., 3(3):57:1--57:22, May 2012. Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. CoRR, abs/1205.2618, 2012. Google ScholarDigital Library
- E. M. Voorhees and D. K. Harman. TREC: Experiment and Evaluation in Information Retrieval (Digital Libraries and Electronic Publishing). The MIT Press, 2005. Google ScholarDigital Library
- J. Wen and W. Zhou. An improved item-based collaborative filtering algorithm based on clustering method. In M. Pathan, G. Wei, and G. Fortino, editors, Journal of Computational Information Systems, volume 8 of Lecture Notes in Computer Science, pages 571--578. Springer Berlin Heidelberg, 2012.Google Scholar
Index Terms
- Group-based Collaborative Filtering Supported by Multiple Users' Feedback to Improve Personalized Ranking
Recommendations
Trust-based collaborative filtering: tackling the cold start problem using regular equivalence
RecSys '18: Proceedings of the 12th ACM Conference on Recommender SystemsUser-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers ...
Collaborative filtering based on an iterative prediction method to alleviate the sparsity problem
iiWAS '09: Proceedings of the 11th International Conference on Information Integration and Web-based Applications & ServicesCollaborative filtering (CF) is one of the most popular recommender system technologies. It tries to identify users that have relevant interests and preferences by calculating similarities among user profiles. The idea behind this method is that, it may ...
Ranking-Oriented Collaborative Filtering: A Listwise Approach
Collaborative filtering (CF) is one of the most effective techniques in recommender systems, which can be either rating oriented or ranking oriented. Ranking-oriented CF algorithms demonstrated significant performance gains in terms of ranking accuracy, ...
Comments