Advertisement

Information Retrieval

, Volume 8, Issue 1, pp 129–150 | Cite as

Scale and Translation Invariant Collaborative Filtering Systems

  • Daniel Lemire
Article

Abstract

Collaborative filtering systems are prediction algorithms over sparse data sets of user preferences. We modify a wide range of state-of-the-art collaborative filtering systems to make them scale and translation invariant and generally improve their accuracy without increasing their computational cost. Using the EachMovie and the Jester data sets, we show that learning-free constant time scale and translation invariant schemes outperforms other learning-free constant time schemes by at least 3% and perform as well as expensive memory-based schemes (within 4%). Over the Jester data set, we show that a scale and translation invariant Eigentaste algorithm outperforms Eigentaste 2.0 by 20%. These results suggest that scale and translation invariance is a desirable property.

recommender system regression incomplete vectors energy minimization e-commerce 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Amrani MYE, Delisle S and Biskri I (2001) Coping with information retrieval problems on the web: Towards personal web weaver agents. In: IC-AI'01, pp. 1225–1231.Google Scholar
  2. Billsus D and Pazzani M (1998) Learning collaborative information filterings. In: AAAI Workshop on Recommender Systems.Google Scholar
  3. Breese JS, Heckerman Dand Kadie C (1998) Empirical analysis of predictive algorithms for collaborative filtering. Technical report, Microsoft Research.Google Scholar
  4. Canny J (2002) Collaborative filtering with privacy via factor analysis. In: SIGIR 2002.Google Scholar
  5. Drineas P, Kerenidis I and Raghavan P (2002) Competitive recommendation systems. In: Proc. of the Thirty-Fourth Annual ACM Symposium on Theory of Computing, pp. 82–90.Google Scholar
  6. Ghahramani Z and Jordan M (1994) Learning from incomplete data. Technical Report 108, MIT Center for Biological and Computational Learning.Google Scholar
  7. Goldberg K, Roeder T, Gupta Dand Perkins C (2001) Eigentaste: Aconstant time collaborative filtering algorithm. Information Retrieval, 4(2):133–151.CrossRefGoogle Scholar
  8. Herlocker J, Konstan J, Borchers A and Riedl J (1999) An algorithmic framework for performing collaborative filtering. In: Proc. of Research and Development in Information Retrieval.Google Scholar
  9. Karypis G (2000) Evaluation of item-based top-N recommendation algorithms. Technical Report 00–046, University of Minnesota, Department of Computer Science.Google Scholar
  10. Pennock DM and Horvitz E (1999) Collaborative filtering by personality diagnosis: A hybrid memory-and model-based approach. In: IJCAI-99.Google Scholar
  11. Pennock DM, Horvitz E and Giles CL (2000) Social choice theory and recommender systems: Analysis of the axiomatic foundations of collaborative filtering. In: AAAI-2000, pp. 729–734.Google Scholar
  12. Resnick P, Iacovou N, Suchak M, Bergstrom P and Riedl J (1994) Grouplens: An open architecture for collaborative filtering of netnews. In: Proc. ACM Computer Supported Cooperative Work, pp. 175–186.Google Scholar
  13. Salton G and Buckley C (1998) Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24(5):513–523.Google Scholar
  14. Sarwar BM, Karypis G, Konstan JA and Riedl JT (2000) Application of dimensionality reduction in recommender system—A case study. In: WEBKDD '00, pp. 82–90.Google Scholar
  15. Sarwar BM, Karypis G, Konstan JA and Riedl J (2001) Item-based collaborative filtering recommender algorithms. In: WWW10.Google Scholar
  16. Vucetic S and Obradovic Z (2000) A regression-based approach for scaling-up personalized recommender systems in E-commerce. In: WEBKDD '00.Google Scholar
  17. Weiss S and Indurkhya N (2001) Lightweight collaborative filtering method for binary encoded data. In: PKDD '01.Google Scholar
  18. Yu K, Xu X, Tao J, Ester Mand Kriegel H-P (2002) Instance selection techniques for memory-based collaborative filtering. In: SDM '02.Google Scholar
  19. Yu K, Xu X, Tao J, Kri ME and Kriegel H-P (2003) Feature weighting and instance selection for collaborative filtering: An information-theoretic approach. Knowledge and Information Systems, 5(2).Google Scholar

Copyright information

© Kluwer Academic Publishers 2005

Authors and Affiliations

  • Daniel Lemire
    • 1
  1. 1.National Research Council of CanadaInstitute for Information TechnologyFrederictonCanada

Personalised recommendations