Username   Password       Forgot your password?  Forgot your username? 


Restricted Boltzmann Machine Collaborative Filtering Recommendation Algorithm based on Project Tag Improvement

Volume 14, Number 6, June 2018, pp. 1109-1118
DOI: 10.23940/ijpe.18.06.p2.11091118

Xiaodong Qiana and Guoliang Liub

aSchool of Economics and Business Administration, Lanzhou Jiaotong University, Lanzhou, 730070, China
bSchool of Traffic and Transportation Engineering, Lanzhou Jiaotong University, Lanzhou, 730070, China

(Submitted on February 16, 2018; Revised on March 28, 2018; Accepted on April 30, 2018)


The collaborative filtering algorithm based on Restricted Boltzmann Machine (RBM) has the problem of heavy weight in the prediction of the “popular project” and poor discrimination of the “unpopular project”, which results in reduced prediction accuracy of the model algorithm. In order to improve the personalization and accuracy of the model, this article integrates project tags into the prediction process based on the RBM model and uses the project tags to describe the user's own interest preference, which strengthens the individual needs of the user: First, it uses projects that the user has already graded to calculate the user's probability of rating the objective tag; Second, it uses the probability of the scoring to predict the probability of different scoring levels of the user's unprotected items; Then, RBM model training is used to predict the probability that the user will score different grades for items that are not scored; Finally, the two scoring probabilities are weighted to the RBM model prediction process to produce prediction results. Experimental results using Movielens datasets show that the accuracy of the proposed method is improved by 1.2% compared with the original algorithm.


References: 13

        1. J. S. Breese, D. Heckerman, C. Kadie, “Empirical Analysis of Predictive Algorithms for Collaborative Filtering”, Fourteenth Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers, Inc, pp.43-52, 1998.
        2. D. Chen, S. Gao, Z. Q. Lin, “A Survey on Recommendation System Algorithm Based on Restricted Boltzmann Machine”, Software, vol.12, pp.156-159, 2013.
        3. J. Gantz, D. Reinsel, “2011 Digital Universe Study: Extracting Value from Chaos”, IDC Go-to-Market Services, 2011.
        4. K. Georgiev, P. Nakov, “A non-IID Framework for Collaborative Filtering with Restricted Boltzmann Machines”, 8International Conference on Machine Learning, pp.1148-1156, 2013.
        5. J. Y. He, B. Ma, “Based on Real-Valued Conditional Restricted Boltzmann Machine and Social Network for Collaborative Filtering”, Chinese Journal of Computers, vol.1, pp.183-195, 2016.
        6. G. Hinton, “Training Products of Experts by Minimizing Contrastive Divergence”, Neural Computation, vol.14, no.8, pp.1771-1800, 2002.
        7. G. Louppe, “Collaborative Filtering: Scalable Approaches Using Restricted Boltzmann Machine”. English, 2010.
        8. H. Luo, “Restricted Boltzmann Machines: A Collaborative Filtering Perspective”, Shanghai Jiao Tong University, 2011.
        9. R. Salakhutdinov, A. Mnih, G. Hinton, “Restricted Boltzmann Machines for Collaborative Filtering”. Machine Learning, Proceedings of the Twenty-Fourth International Conference, pp.791-798, 2007.
        10. G. X. Wang, H. P. Liu, “Survey of Personalized Recommendation System”, Computer Engineering and Applications, Vol 48, pp. 66-76, 2012.
        11. L. Xiang, “Recommender Systems Practice”, The people’s Posts and Telecommunications Press, 2012.
        12. H. L. Xu, X. Wu, X. D. Li, et al., “Comparison Study of Internet Recommendation System”. Journal of Software, vol.20, no.2, pp.350-362, 2009.
        13. C. X. Zhang, N. N. Ji, G. W. Wang, “Restricted Boltzmann Machines. Chinese Journal of Engineering Mathematics”, no.2, pp.159-173, 2015.


              Please note : You will need Adobe Acrobat viewer to view the full articles.Get Free Adobe Reader

              This site uses encryption for transmitting your passwords.