Addressing cold-start problem in recommendation systems

ABSTRACT

Recommender systems for automatically suggested items of interest to users have become increasingly essential in fields where mass personalization is highly valued. The popular core techniques of such systems are collaborative filtering, content-based filtering and combinations of these. In this paper, we discuss hybrid approaches, using collaborative and also content data to address cold-start - that is, giving recommendations to novel users who have no preference on any items, or recommending items that no user of the community has seen yet. While there have been lots of studies on solving the item-side problems, solution for user-side problems has not been seen public. So we develop a hybrid model based on the analysis of two probabilistic aspect models using pure collaborative filtering to combine with users' information. The experiments with MovieLen data indicate substantial and consistent improvements of this model in overcoming the cold-start user-side problem.

References

1. M. Benjamin, "Collaborative Filtering - A Machine Learning Perspective," University of Torronto, 2004.
2. D. Billsus and M. J. Pazzani, "Learning collaborative information filters," Proceedings of the Fifteenth International Conference on Machine Learning, pp. 46--54, 1998.
3. J. S. Breese, D. Heckerman, and C. Kadie, "Empirical analysis of predictive algorithms for collaborative filtering," Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, pp. 34--52, 1998.
4. W. W. Cohen, R. E. Schapire, and Y. Singer, "Learning to order things," Journal of Artificial Intelligence Research, 243--270, 1999.
5. GroupLens Research, www.grouplens.org
6. J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl, "An algorithmic framework for performing collaborative filtering," Proceedings of the Conference on Research and Development in Information Retrieval, 1999.
7. T. Hofmann, "Probabilistic latent semantic analysis," Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, 1999.
8. T. Hofmann and J. Puzicha, "Latent class models for collaborative filtering," Proceedings of the Sixteenth International Join Conference on Artificial Intelligence, pp. 688--693, 1999.
9. R. M. Neal and G. E. Hinton, "A new view of the EM algorithm that justifies incremental, sparse and other variants," Learning in Graphical Models, pp. 355--368, Kluwer Academic Publishers, 1998.
10. D. M. Pennock, E. Horwitz, and C. L. Giles, "Social choice theory and recommender systems: Analysis of the axiomatic foundations of collaborative filtering," Proceedings of the Seventeenth National Conference on Artificial Intelligence, pp. 729--734, 2000.
11. D. M. Pennock, E. Horvitz, S. Lawrence, and C. L. Giles, "Collaborative filtering by personality diagnosis: A hybrid memory - and model-based approach," Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, pp. 473--480, 2000.
12. A. Popescul, L. H. Ungar, D. M. Pennock, and S. Lawrence, "Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments," Proceedings of the Seventeenth Conference on Uncertainty in Aritificial Intelligence, 2001.
13. B. M. Sarwar, G. Karypis, J. A. Konstan, and J. T. Riedle, "Application of dimensionality reduction in recommender system - A case study," ACM WebKDD Web mining for E-Commerce Workshop, 2000.
14. B. M. Sarwar, G. Karypis, J. A. Konstan, and J. T. Riedle, "Item-based collaborative filtering recommendation algorithms," Proceedings of the Tenth International World Wide Web Conference, pp. 285--295, 2001
15. H. Thomas, "Learning What People (Don't) Want," Proceedings of the European Conference on Machine Learning (ECML), 2001.
16. L. H. Ungar and D. P. Foster, "Clustering methods for collaborative filtering," Workshop on Recommendation Systems at the Fifteenth National Conference on Artificial Intelligence, 1998.
17. R. Jin, L. Si, and C. Zhai, "A Study of Mixture Models for Collaborative Filtering," Journal of Information Retrieval, 2006.
18. S. Park, D. Pennock, O. Madani, N. Good and D. DeCoste, "Naive filterbots for Robust Cold-start Recommendations," KDD'06, August 20--23, 2006
19. J. Kleinberg and M. Sandler, "Using Mixture Models for Collaborative Filtering," STOC'04, June 13--15, 2004.
20. E. Savia, K. Puolamaki, J. Sinkkonen, and S. Kaski, "Two-way latent grouping model for user preference prediction," Uncertainty in Artificial Intelligence 21, F. Bacchus and T. Jaakkola, Eds. Corvallis, Oregon: AUAI Press, pp. 518--525, 2005.

Index Terms

• Human-centered computing

  • Collaborative and social computing

• Information systems

  • Information retrieval

    • Evaluation of retrieval results

    • Retrieval tasks and goals

      • Document filtering

      • Information extraction

    • Users and interactive retrieval

      • Personalization

  • World Wide Web

    • Web searching and information discovery

      • Personalization

• Theory of computation

  • Models of computation

    • Probabilistic computation