Collaborative Kalman Filtering for Dynamic Matrix Factorization

We propose a new algorithm for estimation, prediction, and recommendation named the collaborative Kalman filter. Suited for use in collaborative filtering settings encountered in recommendation systems with significant temporal dynamics in user preferences, the approach extends probabilistic matrix factorization in time through a state-space model. This leads to an estimation procedure with parallel Kalman filters and smoothers coupled through item factors. Learning of global parameters uses the expectation-maximization algorithm. The method is compared to existing techniques and performs favorably on both generated data and real-world movie recommendation data.

[1]  John Riedl,et al.  Recommender systems: from algorithms to user experience , 2012, User Modeling and User-Adapted Interaction.

[2]  Xi Chen,et al.  Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization , 2010, SDM.

[3]  Bin Li,et al.  Tracking User-Preference Varying Speed in Collaborative Filtering , 2011, AAAI.

[4]  C. Striebel,et al.  On the maximum likelihood estimates for linear dynamic systems , 1965 .

[5]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[6]  Ameet Talwalkar,et al.  Divide-and-Conquer Matrix Factorization , 2011, NIPS.

[7]  Ruslan Salakhutdinov,et al.  Bayesian probabilistic matrix factorization using Markov chain Monte Carlo , 2008, ICML '08.

[8]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[9]  J. A. Konstan,et al.  Recommended for you , 2012, IEEE Spectrum.

[10]  Mingxuan Sun,et al.  A Comparative Study of Collaborative Filtering Algorithms , 2012, Proceedings of the International Conference on Knowledge Discovery and Information Retrieval.

[11]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[12]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[13]  Kush R. Varshney,et al.  Dynamic matrix factorization: A state space approach , 2011, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[15]  Jun Wang,et al.  Using control theory for stable and efficient recommender systems , 2012, WWW.

[16]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[17]  Yoram Singer,et al.  Local Low-Rank Matrix Approximation , 2013, ICML.

[18]  Anne Boyer,et al.  Target tracking in the recommender space: Toward a new recommender system based on Kalman filtering , 2010, ArXiv.

[19]  Param Vir Singh,et al.  A Hidden Markov Model for Collaborative Filtering , 2010, MIS Q..

[20]  Kaare Brandt Petersen,et al.  The Matrix Cookbook , 2006 .

[21]  J. Meditch,et al.  Applied optimal control , 1972, IEEE Transactions on Automatic Control.

[22]  Yaakov Bar-Shalom,et al.  Optimal simultaneous state estimation and parameter identification in linear discrete-time systems , 1970 .

[23]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[24]  Nathan Srebro,et al.  Learning with matrix factorizations , 2004 .

[25]  Licia Capra,et al.  Temporal collaborative filtering with adaptive neighbourhoods , 2009, SIGIR.

[26]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[27]  Inderjit S. Dhillon,et al.  A spatio-temporal approach to collaborative filtering , 2009, RecSys '09.