Abstract
User tastes are constantly drifting over time as users are exposed to different types of products. The ability to model the tendency of both user preferences and product attractiveness is vital to the success of recommender systems (RSs). We propose a Bayesian Wishart matrix factorization method to model the temporal dynamics of variations among user preferences and item attractiveness in a novel algorithmic perspective. The proposed method is able to well model and properly control diverse rating behaviors across time frames and related temporal effects within time frames in the tendency of user preferences and item attractiveness. We evaluate the proposed method on two synthetic and three real-world benchmark datasets for RSs. Experimental results demonstrate that our proposed method significantly outperforms a variety of state-of-the-art methods in RSs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
We use latent factors and latent vectors interchangeably in this paper.
Note that there are only 20 ratings in total for each user during training in Synthetic2 whereas there are about 35.48 ratings for each user during training in Netflix used later.
In contrary to common situations, the smaller the RMSE value is, the better the method performs. Therefore, we are actually expecting that the AAI curve is below x-axis if the first method in AAI metric is expected to perform better.
According to the exploratory analysis, the standard deviation for the top 20 % users is about 1.44, which is the largest among the three datasets adopted in the experiments.
We use the off-the-shelf timeSVD++ implementation from http://www.librec.net.
BTPF is based on Matlab with C optimization. Other two methods are based on pure Matlab without optimization. Tests are run on a 4-core machine with 3.3G Hz CPU and 8G memory.
References
Agarwal D, Chen B-C, Elango P (2010) Fast online learning through offline initialization for time-sensitive recommendation. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD’10), pp 703–712
Andrieu C, de Freitas N, Doucet A, Jordan M (2003) An introduction to MCMC for machine learning. Mach Learn 50(1–2):5–43
Bauwens L, Laurent S, Rombouts JVK (2006) Multivariate garch models: a survey. J Appl Econom 21(1):79–109
Bishop CM (2006) Pattern recognition and machine learning (information science and statistics). Springer-Verlag, Inc, New York
Charlin L, Ranganath R, McInerney J, Blei DM (2015) Dynamic poisson factorization. In: Proceedings of the 9th ACM conference on recommender systems (RecSys’15), pp 155–162
Chatzis S (2014) Dynamic Bayesian probabilistic matrix factorization. In: Proceedings of the 28th AAAI conference on artificial intelligence (AAAI’14), pp 1731–1737
Chowdhury N, Cai X, Luo C (2015) European conference on machine learning and principles and practice of knowledge discovery in databases (ECMLPKDD’15), chapter BoostMF: Boosted Matrix Factorisation for Collaborative Ranking, pp 3–18
Chua FCT, Oentaryo RJ, Lim E-P (2013) Modeling temporal adoptions using dynamic matrix factorization. In: Proceedings of IEEE 13th international conference on data mining (ICDM’13), pp 91–100
Ding Y, Li X (2005) Time weight collaborative filtering. In: Proceedings of the 14th ACM international conference on information and knowledge management (CIKM’05), pp 485–492
Gao H, Tang J, Liu H (2015) Addressing the cold-start problem in location recommendation using geo-social correlations. Data Min Knowl Disc 29(2):299–323
Green PJ (1995) Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82(4):711–732
James B, Stan L (2007) The netflix prize. In: Proceedings of KDD Cup, pp 3–6
Kantor PB (2009) Recommender systems handbook. Springer, New York
Konstan J, Riedl J (2012) Deconstructing recommender systems. http://spectrum.ieee.org/computing/software/deconstructing-recommender-systems/. Accessed: 28 Aug 2014
Koren Y (2008) Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD’08), pp 447–456
Koren Y (2009) Collaborative filtering with temporal dynamics. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD’09), pp 447–456
Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37
Liang X, Xi C, Tzu-Kuo H, Jeff S, Jaime GC (2010) Temporal collaborative filtering with Bayesian probabilistic tensor factorization. In: Proceedings of 2010 SIAM international conference on data mining (SAM’10), pp 211–222
Ling G, Yang H, King I, Lyu M (2012) Online learning for collaborative filtering. In: Proceedings of the 2012 international joint conference on neural networks (IJCNN’12), pp 1–8
Liu NN, Zhao M, Xiang E, Yang Q (2010) Online evolutionary collaborative filtering. In: Proceedings of the fourth ACM conference on recommender systems (RecSys’10), pp 95–102
Lu Z, Agarwal D, Dhillon IS (2009) A spatio-temporal approach to collaborative filtering. In: Proceedings of the third ACM conference on recommender systems (RecSys’09), pp 13–20
Luo C, Cai X, Chowdhury N (2014) Self-training temporal dynamic collaborative filtering. In: Proceedings of the 18th Pacific-Asia Conference on knowledge discovery and data mining (PAKDD’14), pp 461–472
Matuszyk P, Spiliopoulou M (2014) Selective forgetting for incremental matrix factorization in recommender systems, pp 204–215
McAuley JJ, Leskovec J (2013) From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In: Proceedings of the 22nd international conference on world wide web (WWW’13), pp 897–908
Murray I, Adams RP, MacKay DJC (2010) Elliptical slice sampling. In: Proceedings of the 13th international conference on artificial intelligence and statistics (AISTATS’10), pp 541–548
Rafailidis D, Nanopoulos A (2014) Modeling the dynamics of user preferences in coupled tensor factorization. In: Proceedings of the 8th ACM conference on recommender systems (RecSys’14), pp 321–324
Salakhutdinov R, Mnih A (2008a) Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In: Proceedings of the 25th international conference on machine learning (ICML’08), pp 880–887
Salakhutdinov R, Mnih A (2008b) Probabilistic matrix factorization. In: Neural information processing systems 21 (NIPS’08)
Teh YW, Jordan MI, Beal MJ, Blei DM (2006) Hierarchical dirichlet processes. J Am Stat Assoc 101(476):1566–1581
Vinagre Ja, Jorge AM, Gama J a (2015) An overview on the exploitation of time in collaborative filtering. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 5(5):195–215
Wang J, Sarwar B, Sundaresan N (2011) Utilizing related products for post-purchase recommendation in e-commerce. In: Proceedings of the Fifth ACM conference on recommender systems (RecSys’11), pp 329–332
Wilson A, Ghahramani Z (2011) Generalised Wishart processes. In: Proceedings of the international conference on machine learning (ICML’11), pp 736–744
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible editor: Thomas Gärtner, Mirco Nanni, Andrea Passerini and Celine Robardet.
Rights and permissions
About this article
Cite this article
Luo, C., Cai, X. Bayesian Wishart matrix factorization. Data Min Knowl Disc 30, 1166–1191 (2016). https://doi.org/10.1007/s10618-016-0474-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10618-016-0474-x