ABSTRACT
The item cold-start problem is of a great importance in collaborative filtering (CF) recommendation systems. It arises when new items are added to the inventory and the system cannot model them properly since it relies solely on historical users' interactions (e.g., ratings). Much work has been devoted to mitigate this problem mostly by employing hybrid approaches that combine content-based recommendation techniques or by devoting a portion of the user traffic for exploration to gather interactions from random users. We focus on pure CF recommender systems (i.e., without content or context information) in a realistic online setting, where random exploration is inefficient and smart exploration that carefully selects users is crucial due to the huge flux of new items with short lifespan. We further assume that users arrive randomly one after the other and that the system has to immediately decide whether the arriving user will participate in the exploration of the new items.
For this setting we present ExcUseMe, a smart exploration algorithm that selects a predefined number of users for exploring new items. ExcUseMe gradually excavates the users that are more likely to be interested in the new items and models the new items based on the users' interactions. We evaluated ExcUseMe on several datasets and scenarios and compared it to state-of-the-art algorithms. Experimental results indicate that ExcUseMe is an efficient algorithm that outperforms all other algorithms in all tested scenarios.
Supplemental Material
- D. Agarwal and B.-C. Chen. Regression-based latent factor models. In KDD '09. Google ScholarDigital Library
- M. Aharon, A. Kagian, Y. Koren, and R. Lempel. Dynamic personalized recommendation of comment-eliciting stories. In RecSys '12. Google ScholarDigital Library
- N. Aizenberg, Y. Koren, and O. Somekh. Build your own music recommender by modeling internet radio streams. In WWW '12. Google ScholarDigital Library
- O. Anava, S. Golan, N. Golbandi, Z. Karnin, R. Lempel, O. Rokhlenko, and O. Somekh. Budget-constrained item cold-start handling in collaborative filtering recommenders via optimal design. In WWW '15. Google ScholarDigital Library
- M. Bateni, M. Hajiaghayi, and M. Zadimoghaddam. Submodular secretary problem and extensions. ACM Trans. Algorithms, 9(4), 2013. Google ScholarDigital Library
- G. Dror, N. Koenigstein, and Y. Koren. Yahoo! music recommendations: Modeling music ratings with temporal dynamics and item. In RecSys '11. Google ScholarDigital Library
- J. C. Duchi, E. Hazan, and Y. Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12, 2011. Google ScholarDigital Library
- M. Feldman, J. Naor, and R. Schwartz. Improved competitive ratios for submodular secretary problems (extended abstract). In APPROX-RANDOM '11. Google ScholarDigital Library
- N. Golbandi, Y. Koren, and R. Lempel. Adaptive bootstrapping of recommender systems using decision trees. In WSDM '11. Google ScholarDigital Library
- N. Golbandi, Y. Koren, and R. Lempel. On bootstrapping recommender systems. In CIKM '10. Google ScholarDigital Library
- A. Gunawardana and C. Meek. Tied boltzmann machines for cold start recommendations. In RecSys '08. Google ScholarDigital Library
- A. Gunawardana and C. Meek. A unified approach to building hybrid recommender systems. In RecSys '09. Google ScholarDigital Library
- A. Gupta, A. Roth, G. Schoenebeck, and K. Talwar. Constrained non-monotone submodular maximization: Offline and secretary algorithms. In WINE '10. Google ScholarDigital Library
- A. Kohrs and B. Mérialdo. Improving collaborative filtering for new-users by smart object selection. In ICME '01.Google Scholar
- Y. Koren. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In KDD '08. Google ScholarDigital Library
- Y. Koren. Collaborative filtering with temporal dynamics. Commun. of the ACM, 53(4), 2010. Google ScholarDigital Library
- Y. Koren, R. M. Bell, and C. Volinsky. Matrix factorization techniques for recommender systems. Computer, 42(8), 2009. Google ScholarDigital Library
- S.-L. Lee. Commodity recommendations of retail business based on decision tree induction. Expert Systems with Applications, 37(5), 2010. Google ScholarDigital Library
- G. Linden, B. Smith, and J. York. Amazon. com recommendations: Item-to-item collaborative filtering. Internet Computing, IEEE, 7(1), 2003. Google ScholarDigital Library
- P. McCullagh and J. A. Nelder. Generalized linear models (Second edition). 1989.Google ScholarCross Ref
- S.-T. Park and W. Chu. Pairwise preference regression for cold-start recommendation. In RecSys '09. Google ScholarDigital Library
- A. Paterek. Improving regularized singular value decomposition for collaborative filtering. In KDD '07.Google Scholar
- M. J. Pazzani and D. Billsus. Content-based recommendation systems. The Adaptive Web, 4321, 2007. Google ScholarDigital Library
- A. M. Rashid, I. Albert, D. Cosley, S. K. Lam, S. M. McNee, J. A. Konstan, and J. Riedl. Getting to know you: Learning new user preferences in recommender systems. In IUI '02. Google ScholarDigital Library
- A. M. Rashid, G. Karypis, and J. Riedl. Learning preferences of new users in recommender systems: an information theoretic approach. SIGKDD Explor. Newsl., 10(2), 2008. Google ScholarDigital Library
- B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborative filtering recommendation algorithms. In WWW '01. Google ScholarDigital Library
- G. Takacs, I. Pilaszy, B. Nemeth, and D. Tikk. Investigation of various matrix factorization methods for large recommender systems. In ICDMW '08. Google ScholarDigital Library
Index Terms
- ExcUseMe: Asking Users to Help in Item Cold-Start Recommendations
Recommendations
Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design
WWW '15: Proceedings of the 24th International Conference on World Wide WebIt is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history. The lack of historical ratings results in the user and the item cold-start problems. The ...
User preference representation based on psychometric models
ADC '11: Proceedings of the Twenty-Second Australasian Database Conference - Volume 115Neighbourhood-based collaborative filtering is one of the most popular recommendation techniques, and has been applied successfully in various fields. User ratings are often used by neighbourhood-based collaborative filtering to compute the similarity ...
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