Modeling Users' Dynamic Preference for Personalized Recommendation

Modeling the evolution of users' preference over time is essential for personalized recommendation. Traditional time-aware models like (1) time-window or recency based approaches ignore or deemphasize much potentially useful information, and (2) time-aware collaborative filtering (CF) approaches largely rely on the information of other users, thus failing to precisely and comprehensively profile individual users for personalization. In this paper, for implicit feedback data, we propose a personalized recommendation model to capture users' dynamic preference using Gaussian process. We first apply topic modeling to represent a user's temporal preference in an interaction as a topic distribution. By aggregating such topic distributions of the user's past interactions, we build her profile, where we treat each topic's values at different interactions as a time series. Gaussian process is then applied to predict the user's preference in the next interactions for top-N recommendation. Experiments conducted over two real datasets demonstrate that our approach outperforms the state-of-the-art recommendation models by at least 42:46% and 66:14% in terms of precision and Mean Reciprocal Rank respectively.

[1]  Vanja Josifovski,et al.  Towards a robust modeling of temporal interest change patterns for behavioral targeting , 2013, WWW '13.

[2]  John C. Platt,et al.  Learning a Gaussian Process Prior for Automatically Generating Music Playlists , 2001, NIPS.

[3]  Deepak Agarwal,et al.  fLDA: matrix factorization through latent dirichlet allocation , 2010, WSDM '10.

[4]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[5]  Alexandros Karatzoglou,et al.  Gaussian process factorization machines for context-aware recommendations , 2014, SIGIR.

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

[7]  Min Zhao,et al.  Online evolutionary collaborative filtering , 2010, RecSys '10.

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

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

[10]  Li Li,et al.  An Improved Recommender Based on Hidden Markov Model , 2012, PRICAI.

[11]  Lars Schmidt-Thieme,et al.  Real-time top-n recommendation in social streams , 2012, RecSys.

[12]  Tsvi Kuflik,et al.  Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011) , 2011, RecSys '11.

[13]  H. J. Mclaughlin,et al.  Learn , 2002 .

[14]  Xue Li,et al.  Time weight collaborative filtering , 2005, CIKM '05.

[15]  Fabio Crestani,et al.  Building user profiles from topic models for personalised search , 2013, CIKM.

[16]  Scott Sanner,et al.  Gaussian Process Preference Elicitation , 2010, NIPS.

[17]  Yong Yu,et al.  Collaborative personalized tweet recommendation , 2012, SIGIR '12.

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

[19]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[20]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[21]  John D. Lafferty,et al.  Dynamic topic models , 2006, ICML.

[22]  Ryan P. Adams,et al.  Incorporating side information into probabilistic matrix factorization using Gaussian Processes , 2010 .

[23]  Karl Aberer,et al.  Towards a dynamic top-N recommendation framework , 2014, RecSys '14.

[24]  Xiaohui Yan,et al.  A biterm topic model for short texts , 2013, WWW.

[25]  Zoubin Ghahramani,et al.  Collaborative Gaussian Processes for Preference Learning , 2012, NIPS.

[26]  Jimeng Sun,et al.  Temporal recommendation on graphs via long- and short-term preference fusion , 2010, KDD.

[27]  Tsvi Kuflik,et al.  Workshop on information heterogeneity and fusion in recommender systems (HetRec 2010) , 2010, RecSys '10.

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

[29]  Pabitra Mitra,et al.  Feature weighting in content based recommendation system using social network analysis , 2008, WWW.