A Novel Framework for Top-N Recommendation Based on Non-negative Matrix Tri-Factorization

  • Jin TianEmail author
  • Yingnan Qu
Conference paper


Clustering techniques have been proved effective to deal with the sparsity and scalability problems in collaborative filtering recommender systems. They aim to identify groups of users having similar preferences or items sharing similar topics. In this study, we propose an integrated recommendation framework based on matrix factorization. Firstly, users and items are clustered into multiple groups and a pair of strongly related user group and item group forms a submatrix. Then some traditional collaborative filtering technique is executed in every submatrix. The final rating predictions are generated by aggregating results from all the submatrices and the items are recommended with a Top-N strategy. Experimental results show that the proposed framework significantly improves the recommendation accuracy of several state-of-the-art collaborative filtering methods, while retains the advantage of good scalability.


Matrix tri-factorization Collaborative filtering Co-clustering Personalized recommendation 



The work was supported by the General Program of the National Science Foundation of China (Grant No. 71471127, 71371135).


  1. 1.
    G. Guo, J. Zhang, N. Yorke-Smith, Leveraging multiviews of trust and similarity to enhance clustering-based recommender systems. Knowl.-Based Syst. 74(1), 14–27 (2015)CrossRefGoogle Scholar
  2. 2.
    B. Li, Q. Yang, X. Xue, Can movies and books collaborate? Cross-domain collaborative filtering for sparsity reduction, in Proceedings of the 21st International Jont Conference on Artifical Intelligence, Pasadena, California, USA, pp. 2052–2057, 2009Google Scholar
  3. 3.
    Z. Huang, D. Zeng, H. Chen et al., A comparison of collaborative-filtering recommendation algorithms for e-commerce. IEEE Intell. Syst. 22(5), 68–78 (2007)CrossRefGoogle Scholar
  4. 4.
    Z. Li, X. Wu, Weighted nonnegative matrix tri-factorization for co-clustering, in 23rd IEEE International Conference on Tools with Artificial Intelligence, Boca Raton, FL, USA, pp. 811–816 (2011)Google Scholar
  5. 5.
    B. Xu, J. Bu, C. Chen et al., An exploration of improving collaborative recommender systems via user-item subgroups, in Proceedings of the 21st International Conference on World Wide Web, Lyon, France, pp. 21–30 (2012)Google Scholar
  6. 6.
    J. Liu, Y. Jiang, Z. Li et al., Domain-sensitive recommendation with user-item subgroup analysis. IEEE Trans. Knowl. Data Eng. 28(4), 939–950 (2016)CrossRefGoogle Scholar
  7. 7.
    Y. Zhang, M. Zhang, Y. Liu et al., Improve collaborative filtering through bordered block diagonal form matrices, in International ACM SIGIR Conference on Research and Development in Information Retrieval, Dublin, Ireland, pp. 313–322 (2013)Google Scholar
  8. 8.
    C. Ding, X. He, H.D. Simon et al., On the equivalence of nonnegative matrix factorization and spectral clustering, in Proceedings of the SIAM International Conference on Data Mining, pp. 606–610 (2005)Google Scholar
  9. 9.
    Q. Gu, J. Zhou, C. Ding et al., Collaborative filtering: weighted nonnegative matrix factorization incorporating user and item graphs, in Proceedings of the SIAM International Conference on Data Mining, pp. 199–210 (2010)Google Scholar
  10. 10.
    G. Chen, F. Wang, C. Zhang et al., Collaborative filtering using orthogonal nonnegative matrix tri-factorization. Inf. Process. Manage. 45(3), 368–379 (2009)CrossRefGoogle Scholar
  11. 11.
    H. Langseth, T.D. Nielsen, Scalable learning of probabilistic latent models for collaborative filtering. Decis. Support Syst. 74, 1–11 (2015)CrossRefGoogle Scholar
  12. 12.
    B. Sarwar, G. Karypis, J. Konstan et al., Application of dimensionality reduction in recommender system—a case study, in ACM Webkdd Workshop (2000)Google Scholar
  13. 13.
    H. Shan, A. Banerjee, Generalized probabilistic matrix factorizations for collaborative filtering, in IEEE 10th International Conference on Data Mining, Sydney, NSW, Australia, pp. 1025–1030 (2010)Google Scholar
  14. 14.
    J.S. Breese, D. Heckerman, C.M. Kadie et al., Empirical analysis of predictive algorithms for collaborative filtering, in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, Madison, Wisconsin, USA, pp. 43–52 (1998)Google Scholar
  15. 15.
    Z. Kang, C. Peng, Q. Cheng, Top-N recommender system via matrix completion, in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA, pp. 179–184 (2016)Google Scholar
  16. 16.
    P. Cremonesi, Y. Koren, R. Turrin, Performance of recommender algorithms on top-n recommendation tasks, in Proceedings of the Fourth ACM Conference on Recommender Systems, Barcelona, Spain, pp. 39–46 (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.College of Management and EconomicsTianjin UniversityTianjinChina

Personalised recommendations