Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Three-way recommendation integrating global and local information

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 19/07/2018, Accepted 26/07/2018, Published 16/08/2018

The matrix factorisation approach computes a low-rank approximation of the incomplete user-item rating matrix. Existing approaches suffer from under-fitting due to the use of global information for all users and items. In this study, the authors propose a three-way recommendation model that integrates global and local information. This new model has a number of main aspects. The first is rating prediction with global and local information. A clustering and two matrix factorisation algorithms are employed for this purpose. The second is the computation of recommendation thresholds based on the decision-theoretic rough set model. Misclassification and promotion costs are considered simultaneously to build the cost matrix. The last is the determination of the recommender actions based on the prediction and thresholds. Experimental results on the well-known datasets show that authors’ proposed model improves recommendation quality in terms of average cost.

Inspec keywords: recommender systems; matrix decomposition; rough set theory; decision theory; approximation theory

Other keywords: incomplete user-item rating matrix; decision-theoretic rough set model; matrix factorisation approach; three-way recommendation model; matrix factorisation algorithms; recommendation quality; cost matrix; recommender actions; local information; global information; recommendation thresholds; rating prediction; low-rank approximation

Subjects: Combinatorial mathematics; Linear algebra (numerical analysis); Interpolation and function approximation (numerical analysis); Information networks

References

    1. 1)
      • 16. Smola, A.J., Schölkopf, B.: ‘Sparse greedy matrix approximation for machine learning’. Int. Conf. on Machine Learning, 2000, pp. 911–918.
    2. 2)
      • 29. Bertsekas, D.P.: ‘Constrained optimization and Lagrange multiplier methods’ (Academic Press, New York, 2014, 1st edn.).
    3. 3)
      • 33. Fenton, N., Neil, M.: ‘Risk assessment and decision analysis with Bayesian networks’ (CRC Press, Boca Raton, 2012, 1st edn.).
    4. 4)
      • 19. Srebro, N., Jaakkola, T.: ‘Weighted low-rank approximations’. Proc. of the 20th Int. Conf. on Machine Learning (ICML-03), 2003, pp. 720–727.
    5. 5)
      • 12. Yao, Y.: ‘The superiority of three-way decisions in probabilistic rough set models’, Inf. Sci., 2011, 181, (6), pp. 1080–1096.
    6. 6)
      • 23. Liu, X.Y., Zhou, Z.H.: ‘The influence of class imbalance on cost-sensitive learning: An empirical study’. Sixth Int. Conf. on IEEE, 2006, pp. 970–974.
    7. 7)
      • 18. Billsus, D., Pazzani, M.J.: ‘Learning collaborative information filters’. AAAI Tech. Report, 1998, vol. 98, pp. 46–54.
    8. 8)
      • 5. Sarwar, B., Karypis, G., Konstan, J., et al: ‘Incremental singular value decomposition algorithms for highly scalable recommender systems’. Int. Conf. on Computer and Information Science, 2002, pp. 27–28.
    9. 9)
      • 22. Ma, H., Yang, H., King, I., et al: ‘Semi-nonnegative matrix factorization with global statistical consistency for collaborative filtering’. Proc. of the 18th ACM Conf. on Information and Knowledge Management, 2009, pp. 767–776.
    10. 10)
      • 24. Yang, X., Yao, J.: ‘Modelling multi-agent three-way decisions with decision-theoretic rough sets’, Fundam. Inform., 2012, 115, (2–3), pp. 157–171.
    11. 11)
      • 8. Huang, J., Wang, J., Yao, Y., et al: ‘Cost-sensitive three-way recommendations by learning pair-wise preferences’, Int. J. Approx. Reason., 2017, 86, pp. 28–40.
    12. 12)
      • 10. Zhang, H.R., Min, F., Shi, B.: ‘Regression-based three-way recommendation’, Inf. Sci., 2017, 378, (1), pp. 444–461.
    13. 13)
      • 11. Yao, Y.: ‘Three-way decisions with probabilistic rough sets’, Inf. Sci., 2010, 180, (3), pp. 341–353.
    14. 14)
      • 9. Zhang, H.R., Min, F.: ‘Three-way recommender systems based on random forests’, Knowl.-Based Syst., 2016, 91, pp. 275–286.
    15. 15)
      • 14. Hartigan, J.A., Wong, M.A.: ‘Algorithm AS 136: A k-means clustering algorithm’, J. Roy. Stat. Soc., 1979, 28, (1), pp. 100–108.
    16. 16)
      • 32. Willmott, C.J., Matsuura, K.: ‘Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance’, Clim. Res., 2005, 30, (1), pp. 79–82.
    17. 17)
      • 34. Ji, S., Carin, L.: ‘Cost-sensitive feature acquisition and classification’, Pattern Recognit., 2007, 40, (5), pp. 1474–1485.
    18. 18)
      • 20. Lee, J., Kim, S., Lebanon, G., et al: ‘Local low-rank matrix approximation’. Int. Conf. on Machine Learning, 2013, pp. 82–90.
    19. 19)
      • 7. Li, T., Wang, J., Chen, H., et al: ‘A NMF-based collaborative filtering recommendation algorithm’. The Sixth World Congress on Intelligent Control and Automation, 2006, vol. 2, pp. 6082–6086.
    20. 20)
      • 25. Li, H., Zhang, L., Huang, B., et al: ‘Sequential three-way decision and granulation for cost-sensitive face recognition’, Knowl.-Based Syst., 2016, 91, pp. 241–251.
    21. 21)
      • 27. Schaffer, J.D., Lee, K.P., Gutta, S.: ‘Three-way media recommendation method and system’. U.S. Patent 7,937,725, May 2011.
    22. 22)
      • 30. Chu, D., Mehrmann, V., Nichols, N.K.: ‘Minimum norm regularization of descriptor systems by mixed output feedback’, Linear Algebr. Appl., 1999, 296, (1–3), pp. 39–77.
    23. 23)
      • 21. Furnas, G.W., Deerwester, S., Dumais, S.T., et al: ‘Information retrieval using a singular value decomposition model of latent semantic structure’. Proc. of the 11th Annual Int. ACM SIGIR Conf. on Research and Development in Information Retrieval, 1988, vol. 51, (2), pp. 465–480.
    24. 24)
      • 28. Liu, D., Li, T., Liang, D.: ‘Three-way government decision analysis with decision-theoretic rough sets’, Int. J. Uncertain. Fuzziness Knowl.-Based Syst., 2012, 20, (supp01), pp. 119–132.
    25. 25)
      • 26. Li, H., Zhou, X., Huang, B., et al: ‘Cost-sensitive three-way decision: a sequential strategy’. Int. Conf. on Rough Sets and Knowledge Technology, 2013, pp. 325–337.
    26. 26)
      • 6. Lee, D.D., Seung, H.S.: ‘Learning the parts of objects by non-negative matrix factorization’, Nature, 1999, 401, (6755), pp. 788–791.
    27. 27)
      • 31. Pong, T.K., Tseng, P., Ji, S., et al: ‘Trace norm regularization: reformulations, algorithms, and multi-task learning’, SIAM J. Optim., 2010, 20, (6), pp. 3465–3489.
    28. 28)
      • 15. Joyce, J.M.: ‘Kullback-Leibler divergence’, in Miodrag, L. (Ed.): ‘International encyclopedia of statistical science’ (Springer, Berlin Heidelberg, 2011), pp. 720–722.
    29. 29)
      • 2. Salakhutdinov, R., Mnih, A.: ‘Bayesian probabilistic matrix factorization using Markov chain Monte Carlo’. Proc. of the 25th Int. Conf. on Machine Learning, 2008, pp. 880–887.
    30. 30)
      • 35. Harper, F.M., Konstan, J.A.: ‘The MovieLens datasets: history and context’, ACM Trans. Inter. Intell. Syst. (TIIS), 2016, 5, (4), pp. 1–20.
    31. 31)
      • 3. Yang, W.F., Wang, M., Chen, Z.: ‘Fast probabilistic matrix factorization for recommender system’. Int. Conf. on Mechatronics and Automation (ICMA), 2014, pp. 1889–1894.
    32. 32)
      • 13. Min, F., He, H., Qian, Y., et al: ‘Test-cost-sensitive attribute reduction’, Inf. Sci., 2011, 181, (22), pp. 4928–4942.
    33. 33)
      • 1. Salakhutdinov, R., Mnih, A.: ‘Probabilistic matrix factorization’. Proc. of the 20th Int. Conf. on Neural Information Processing Systems, Vancouver, Canada, 2008, pp. 1257–1264.
    34. 34)
      • 4. Ma, C.C.: ‘A guide to singular value decomposition for collaborative filtering’. Computer, Long Beach, CA, 2008, pp. 1–14.
    35. 35)
      • 17. Yao, Y.: ‘Three-way decision: an interpretation of rules in rough set theory’. Int. Conf. on Rough Sets and Knowledge Technology, 2009, pp. 642–649.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.8300
Loading

Related content

content/journals/10.1049/joe.2018.8300
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address