A real-time recommender system based on hybrid collaborative filtering
Yuanhong Wu, Xiaoqiu Tan · 2010
In this paper, Singular Value Decomposition (SVD) is combined with hybrid collaborative filtering (CF), proved to be an effective solution for sparsity problem. SVD is utilized in order to reduce the dimension of the user-pageview matrix obtained from web usage mining. Afterwards, both low-rank matrices are employed in order to generate item-based and user-based predictions. A framework for building automatic webpage recommendations in real-time platforms is designed. The recommendation engine which occurs in the online phase gets the user's request and provids the recommended links in real time. Empirical studies on Movie Lens dataset show that our new proposed approach consistently outperforms other algorithms.