Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.

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

[2]  Stathes Hadjiefthymiades,et al.  Facing the cold start problem in recommender systems , 2014, Expert Syst. Appl..

[3]  Preslav Nakov,et al.  A non-IID Framework for Collaborative Filtering with Restricted Boltzmann Machines , 2013, ICML.

[4]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[5]  Xiao Yingyuan,et al.  Time-ordered collaborative filtering for news recommendation , 2015, China Communications.

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

[7]  David M. Pennock,et al.  Generative Models for Cold-Start Recommendations , 2001 .

[8]  Michael R. Lyu,et al.  Learning to recommend with explicit and implicit social relations , 2011, TIST.

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

[10]  Rafael Valencia-García,et al.  Solving the cold-start problem in recommender systems with social tags , 2010, Expert Syst. Appl..

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

[12]  James Bennett,et al.  The Netflix Prize , 2007 .

[13]  Martha Larson,et al.  Collaborative Filtering beyond the User-Item Matrix , 2014, ACM Comput. Surv..

[14]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[15]  Arindam Banerjee,et al.  Generalized Probabilistic Matrix Factorizations for Collaborative Filtering , 2010, 2010 IEEE International Conference on Data Mining.

[16]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[17]  Deepak Agarwal,et al.  Regression-based latent factor models , 2009, KDD.

[18]  Geoffrey E. Hinton,et al.  Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

[19]  Joze Rugelj,et al.  Improving matrix factorization recommendations for examples in cold start , 2015, Expert Syst. Appl..

[20]  Yong Yu,et al.  SVDFeature: a toolkit for feature-based collaborative filtering , 2012, J. Mach. Learn. Res..

[21]  Ke Wang,et al.  Latent Factor Transition for Dynamic Collaborative Filtering , 2014, SDM.

[22]  Chris Cornelis,et al.  Whom should I trust?: the impact of key figures on cold start recommendations , 2008, SAC '08.

[23]  Ebru Arisoy,et al.  Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[24]  Naixue Xiong,et al.  Cold-Start Recommendation Using Bi-Clustering and Fusion for Large-Scale Social Recommender Systems , 2014, IEEE Transactions on Emerging Topics in Computing.

[25]  Dennis M. Wilkinson,et al.  Large-Scale Parallel Collaborative Filtering for the Netflix Prize , 2008, AAIM.

[26]  Shuang-Hong Yang,et al.  Functional matrix factorizations for cold-start recommendation , 2011, SIGIR.

[27]  Guandong Xu,et al.  Personalized recommendation via cross-domain triadic factorization , 2013, WWW.

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

[29]  Xuezhi Tan,et al.  Low complexity multiuser detection with recursively successive zero-forcing and SIC based on nullspace for multiuser MIMO-OFDM system , 2015 .

[30]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[31]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..