Can Matrix Factorization Improve the Accuracy of Recommendations Provided to Grey Sheep Users?

Benjamin Gras, Armelle Brun, Anne Boyer

2017

Abstract

Matrix Factorization (MF)-based recommender systems provide on average accurate recommendations, they do consistently fail on some users. The literature has shown that this can be explained by the characteristics of the preferences of these users, who only partially agree with others. These users are referred to as Grey Sheep Users (GSU). This paper studies if it is possible to design a MF-based recommender that improves the accuracy of the recommendations provided to GSU. We introduce three MF-based models that have the characteristic to focus on original ways to exploit the ratings of GSU during the training phase (by selecting, weighting, etc.). The experiments conducted on a state-of-the-art dataset show that it is actually possible to design a MF-based model that significantly improves the accuracy of the recommendations, for most of GSU.

References

  1. Bellogín, A., Said, A., and de Vries, A. (2014). The magic barrier of recommender systems - no magic, just ratings. In Proc. of the 22nd Conf. on User Modelling, Adaptation and Personalization (UMAP).
  2. Bobadilla, J., Ortega, F., and Hernando, A. (2012). A collaborative filtering similarity measure based on singularities. Inf. Process. Manage., 48:204-217.
  3. Castagnos, S., Brun, A., and Boyer, A. (2013). When diversity is needed... but not expected! In IMMM 2013, The Third Int. Conf. on Advances in Information Mining and Management.
  4. Claypool, M., Gokhale, A., and Miranda, T. (1999). Combining content-based and collaborative filters in an online newspaper. In Proceedings of the SIGIR Workshop on Recommender Systems: Algorithms and Evaluation.
  5. Del Prete, L. and Capra, L. (2010). differs: A mobile recommender service. In Proc. of the 2010 Eleventh Int. Conf. on Mobile Data Management, MDM 7810, pages 21-26, Washington, USA. IEEE Computer Society.
  6. Ghazanfar, M. and Prugel-Bennett, A. (2011). Fulfilling the needs of gray-sheep users in recommender systems, a clustering solution. In 2011 Int. Conf. on Information Systems and Computational Intelligence.
  7. Ghazanfar, M. A. and A., P.-B. (2014). Leveraging clustering approaches to solve the gray-sheep users problem in recommender systems. Expert Systems with Applications, 41:3261-3275.
  8. Goldberg, D., Nichols, D., Oki, B., and Terry, D. (1992). Using collaborative filtering to weave an information tapestry. Communications of the ACM, 35:61-70.
  9. Gras, B., Brun, A., and Anne, B. (2016). Identifying Grey Sheep Users in Collaborative Filtering: a DistributionBased Technique. In ACM UMAP, page 9, Halifax, Canada.
  10. Grcar, M., Mladenic, D., Fortuna, B., and Grobelnik, M. (2005a). Advances in Web Mining and Web Usage Analysis, volume 4198, chapter Data Sparsity Issues in the Collaborative Filtering Framework, pages 58- 76. Springer.
  11. Grcar, M., Mladenic, D., and Grobelnik, M. (2005b). Data quality issues in collaborative filtering. In Proc. of ESWC-2005 Workshop on End User Aspects of the Semantic Web.
  12. Griffith, J., O'Riordan, C., and Sorensen, H. (2012). Investigations into user rating information and predictive accuracy in a collaborative filtering domain. InProc. of the 27th ACM Symposium on Applied Computing.
  13. Huang, S. (2011). Designing utility-based recommender systems for e-commerce: Evaluation of preferenceelicitation methods. Electronic Commerce Research and Applications, 10(4).
  14. Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42:30-37.
  15. Manouselis, N., Kyrgiazos, G., and Stoitsis, G. (2014). Exploratory study of multi-criteria recommendation algorithms over technology enhanced learning datasets. Journal of e-Learning and Knowledge Society, 10(1).
  16. Ng, A. Y. (2004). Feature selection, l1 vs. l2 regularization, and rotational invariance. In Proceedings of the Twenty-first International Conference on Machine Learning, ICML 7804, pages 78-, New York, NY, USA. ACM.
  17. Nigam, K. (1999). Using maximum entropy for text classification. InIn IJCAI-99 Workshop on Machine Learning for Information Filtering, pages 61-67.
  18. Penn, M. and Zalesne, K. (2007). Mircotrends: the small forces behind tomorrow's big changes. Twelve.
  19. Rashid, A., Lam, S., LaPitz, A., Karypis, G., and Riedl, J. (2008). Web Mining and Web Usage Analysis, chapter Towards a Scalable kNN CF Algorithm: Exploring Effective Applications of Clustering. Springer.
  20. Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., and Riedl, J. (1994). Grouplens: An open architecture for collaborative filtering of netnews. In Proc. of the 1994 ACM Conf. on Computer Supported Cooperative Work, CSCW'94.
  21. Schickel-Zuber, V. and Faltings, B. (2006). Overcoming incomplete user models in recommendation systems via an ontology. In Proc. of the 7th Int. Conf. on Knowledge Discovery on the Web, WebKDD'05, pages 39- 57, Berlin. Springer.
  22. Takacs, G., Pilaszy, I., Nemeth, B., and Tikk, D. (2009). Scalable collaborative filtering approaches for large recommender systems. Journal of Machine Learning Research, 10:623-656.
  23. Verbert, K., Manouselis, N., Ochoa, X., and Wolpers, M. (2012). Context-aware recommender systems for learning: A survey and future challenges. IEEE Transactions on Learning Technologies, 5.
  24. Yu, H.-F., Hsieh, C.-J., Si, S., and Dhillon, I. S. (2014). Parallel matrix factorization for recommender systems. Knowl. Inf. Syst., 41:793-819.
  25. Zanker, M., Fuchs, M., Höpken, W., Tuta, M., and Muller, N. (2008). Information and communication technologies in tourism, chapter Evaluating recommender systems in tourism a case study from austria. Springer.
  26. Zheng, A. X., Jordan, M. I., Liblit, B., and Aiken, A. (2004). Statistical debugging of sampled programs. In Thrun, S., Saul, L. K., and Schölkopf, B., editors, Advances in Neural Information Processing Systems 16, pages 603-610. MIT Press.
Download


Paper Citation


in Harvard Style

Gras B., Brun A. and Boyer A. (2017). Can Matrix Factorization Improve the Accuracy of Recommendations Provided to Grey Sheep Users? . In Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-246-2, pages 88-96. DOI: 10.5220/0006302700880096


in Bibtex Style

@conference{webist17,
author={Benjamin Gras and Armelle Brun and Anne Boyer},
title={Can Matrix Factorization Improve the Accuracy of Recommendations Provided to Grey Sheep Users?},
booktitle={Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2017},
pages={88-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006302700880096},
isbn={978-989-758-246-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Can Matrix Factorization Improve the Accuracy of Recommendations Provided to Grey Sheep Users?
SN - 978-989-758-246-2
AU - Gras B.
AU - Brun A.
AU - Boyer A.
PY - 2017
SP - 88
EP - 96
DO - 10.5220/0006302700880096