Paolo Cremonesi
ABSTRACT
In this paper we evaluate the performance of different collaborative filtering algorithms over time, where new users, new items, and new ratings are constantly added to the recommender dataset.
The analysis has been performed on the datasets collected by two IPTV providers. Both datasets have been implicitly collected by analyzing the pay-per-view movies purchased by the users over a period of several months. The first result of the paper outlines that item-based algorithms perform better with respect to SVD-based ones in the early stage of the cold-start problem. The second result shows that the accuracy of SVD-based algorithms, when using few latent factors, decreases with the time-evolution of the dataset. On the contrary, SVD-based algorithms, when used with a large-enough number of latent features, increase their accuracy with time and may outperform the item-based algorithms if the dataset does not present a long-tail behavior.
- J. F. Abreu, P. Almeida, R. Pinto, and V. Nobre. Implementation of social features over regular iptv stb. In "EuroITV '09: Proceedings of the seventh european conference on European interactive television conference", pages 29--32, New York, NY, USA, 2009. ACM. Google Scholar
Digital Library
- G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. In "Knowledge and Data Engineering, IEEE Transactions on", 17(6):734--749, 2005. Google ScholarDigital Library
- H. J. Ahn. A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. In "Inf. Sci.", 178(1):37--51, 2008. Google ScholarDigital Library
- J. Bennett and S. Lanning. The Netflix Prize. In "Proceedings of KDD Cup and Workshop", pages 3--6, 2007.Google Scholar
- E. Campochiaro, R. Casatta, P. Cremonesi, and R. Turrin. Do metrics make recommender algorithms? In "IEEE Advanced Information Networking and Applications (AINA)", 2009. Google ScholarDigital Library
- O. Celma and P. Cano. From hits to niches? or how popular artists can bias music recommendation and discovery. Las Vegas, USA, August 2008.Google Scholar
- O. Celma and P. Herrera. A new approach to evaluating novel recommendations. In "RecSys '08: Proceedings of the 2008 ACM conference on Recommender systems", pages 179--186, New York, NY, USA, 2008. ACM. Google ScholarDigital Library
- P. Cremonesi, E. Lentini, M. Matteucci, and R. Turrin. An evaluation methodology for recommender systems. In "4th Int. Conf. on Automated Solutions for Cross Media Content and Multi-channel Distribution", pages 224--231, Nov 2008. Google ScholarDigital Library
- P. Cremonesi and R. Turrin. Analysis of cold-start recommendations in iptv systems. In "RecSys '09: Proceedings of the 2009 ACM conference on RecommenderSystems", pages 1--4. ACM, 2009. Google ScholarDigital Library
- T. De Pessemier, T. Deryckere, and L. Martens. Context aware recommendations for user-generated content on a social network site. In "EuroITV '09: Proceedings of the seventh european conference on European interactive television conference", pages 133--136, New York, NY, USA, 2009. ACM. Google ScholarDigital Library
- M. Deshpande and G. Karypis. Item-based top-n recommendation algorithms. In "ACM Transactions on Information Systems (TOIS)", 22(1):143--177, 2004. Google ScholarDigital Library
- G. W. Furnas, S. Deerwester, S. T. Dumais, T. K. Landauer, R. A. Harshman, L. A. Streeter, and K. E. Lochbaum. Information retrieval using a singular value decomposition model of latent semantic structure. pages 465--480, New York, NY, USA, 1988. ACM Press.Google Scholar
- A. Gunawardana and C. Meek. Tied boltzmann machines for cold start recommendations. In "RecSys '08: Proceedings of the 2008 ACM conference on Recommender systems", pages 19--26, New York, NY, USA, 2008. ACM. Google ScholarDigital Library
- J. Herlocker, J. Konstan, and J. Riedl. An algorithmic framework for performing collaborative filtering". In "22nd ACM SIGIR Conf. on R&D in Information Retrieval", pages 230--237, 1999. Google ScholarDigital Library
- J. Herlocker, J. Konstan, L. Terveen, and J. Riedl. Evaluating collaborative filtering recommender systems". In "ACM Transactions on Information Systems (TOIS)", 22(1):5--53, 2004. Google ScholarDigital Library
- J. L. Herlocker, J. A. Konstan, and J. Riedl. Explaining collaborative filtering recommendations. pages 241--250, New York, NY, USA, 2000. ACM. Google ScholarDigital Library
- Z. Huang, H. Chen, and D. Zeng. Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering. In "ACM Trans. Inf. Syst.", 22(1):116--142, 2004. Google ScholarDigital Library
- P. Husbands, H. Simon, and C. Ding. On the use of singular value decomposition for text retrieval. Oct. 2000.Google Scholar
- P. Lops, M. Degemmis, and G. Semeraro. Improving social filtering techniques through wordnet-based user profiles. In "UM '07: Proceedings of the 11th international conference on User Modeling", pages 268--277, Berlin, Heidelberg, 2007. Springer-Verlag. Google ScholarDigital Library
- A.-T. Nguyen, N. Denos, and C. Berrut. Improving new user recommendations with rule-based induction on cold user data. In "RecSys '07: Proceedings of the 2007 ACM conference on Recommender systems", pages 121--128, New York, NY, USA, 2007. ACM. Google ScholarDigital Library
- S.-T. Park, D. Pennock, O. Madani, N. Good, and D. DeCoste. Naïve filterbots for robust cold-start recommendations. In KDD '06: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining", pages 699--705, New York, NY, USA, 2006. ACM. Google ScholarDigital Library
- A. Paterek. Improving regularized singular value decomposition for collaborative filtering. In "Proceedings of KDD Cup and Workshop", 2007. Google ScholarDigital Library
- B. Sarwar, G. Karypis, J. Konstan, and J. Reidl. Item-based collaborative filtering recommendation algorithms". In "10th Int. Conf. on World Wide Web", pages 285--295, 2001. Google ScholarDigital Library
- B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Incremental singular value decomposition algorithms for highly scalable recommender systems". In "5th Int. Conf. on Computer and Information Technology (ICCIT 2002)", pages 399--404, 2002.Google Scholar
- A. Schein, A. Popescul, L. Ungar, and D. Pennock. Generate models for cold-start recommendations. In "ACMSIGIR Workshop on RecommenderSystems.", 2001. Google ScholarDigital Library
- A. Schein, A. Popescul, L. Ungar, and D. Pennock. Methods and metrics for cold-start recommendations. In "Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2002)", pages 253--260, 2002. Google ScholarDigital Library
- G. Takács, I. Pilászy, B. Németh, and D. Tikk. Scalable collaborative filtering approaches for large recommender systems. In "J. Mach. Learn. Res.", 10:623--656, 2009. Google ScholarDigital Library
- E. Vozalis and K. Margaritis. Analysis of recommender systems algorithms". In "Proc. of the 6th Hellenic European Conf. on Computer Mathematics and its Applications", 2003.Google Scholar
- J. Zaletelj, M. Savić", and M. Meža. Real-time viewer feedback in the itv production. In "EuroITV '09: Proceedings of the seventh european conference on European interactive television conference", pages 149--152, New York, NY, USA, 2009. ACM. Google ScholarDigital Library
Index Terms
- Time-evolution of IPTV recommender systems
Recommendations
An effective recommender system by unifying user and item trust information for B2B applications
Although Collaborative Filtering (CF)-based recommender systems have received great success in a variety of applications, they still under-perform and are unable to provide accurate recommendations when users and items have few ratings, resulting in ...
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 ...
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data MiningRecommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
Comments