Dynamic Model Adaptive to User Interest Drift Based on Cluster and Nearest Neighbors

A recommendation system provides personalized recommendations on products and services to users. In the traditional recommendation system, the user interest is regarded as constant over time, while in fact, the user interest changes over time. Hence, tracking the user interest drift becomes key in designing the dynamic recommendation system. However, it is a challenge to find an accurate and effective method that can predict the user interest drift. To solve the prediction problem of the user interest drift, this paper adopts clustering and time impact factor matrix to monitor the degree of user interest drift in the class and more accurately predict an item’s rating. We add a time impact factor to the original baseline estimates and use the linear regression to predict the user interest drift. Our comparative experiments are conducted on three big data sets: MovieLens100K, MovieLens1M, and MovieLens10M. The experimental results show that our proposed approach can efficiently improve the prediction accuracy.

[1]  Wu Sen,et al.  A Collaborative Filtering Recommender System Integrated with Interest Drift based on Forgetting Function , 2015 .

[2]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[3]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[4]  Yi Zhang,et al.  Novelty and redundancy detection in adaptive filtering , 2002, SIGIR '02.

[5]  Ning Ye,et al.  Time-Aware Collaborative Filtering for Recommender Systems , 2012, CCPR.

[6]  Gerhard Widmer,et al.  Learning in the presence of concept drift and hidden contexts , 2004, Machine Learning.

[7]  Latha Banda,et al.  Evaluation of Collaborative Filtering Based on Tagging with Diffusion Similarity Using Gradual Decay Approach , 2014 .

[8]  Yehuda Koren,et al.  Factor in the neighbors: Scalable and accurate collaborative filtering , 2010, TKDD.

[9]  Dong Liu,et al.  Category-based dynamic recommendations adaptive to user interest drifts , 2014, 2014 Sixth International Conference on Wireless Communications and Signal Processing (WCSP).

[10]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

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

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

[13]  Yuzhao Liu,et al.  A Collaborative Filtering Algorithm Based on Time Period Partition , 2010, 2010 Third International Symposium on Intelligent Information Technology and Security Informatics.

[14]  Yehuda Koren,et al.  Yahoo! music recommendations: modeling music ratings with temporal dynamics and item taxonomy , 2011, RecSys '11.

[15]  Madhu Yedla,et al.  Enhancing K-means Clustering Algorithm with Improved Initial Center , 2010 .

[16]  Nipa Chowdhury,et al.  Probabilistic temporal bilinear model for temporal dynamic recommender systems , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[17]  Clara E. Bussenius,et al.  Memory : A Contribution to Experimental Psychology , 2017 .

[18]  Guokun Lai,et al.  Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis , 2015, WWW.

[19]  Jean-Michel Renders,et al.  Time-Sensitive Collaborative Filtering through Adaptive Matrix Completion , 2015, ECIR.

[20]  Feng Zhao,et al.  Privacy-Preserving Collaborative Filtering Based on Time-Drifting Characteristic , 2016 .