Improved collaborative filtering model based on context clustering and user ranking
Deng Xiao-y · Systems Engineering - Theory & Practice · 2013
The collaborative filtering(CF) is an important technique to provide personalized recommendation in e-commerce.In spite of its huge success,CF suffers from several problems,such as the ratings data sparsity.Meanwhile,traditional CF is unable to distinguish users who have similar tastes but with different rating behaviors.Besides,traditional CF methods don't consider that customers' interests and demands may vary with contexts in mobile environment.To address these problems,this paper proposes an improved collaborative filtering model based on context clustering and user ranking.This model works in two phases.In the first phase,all users are clustered into groups with similar context to reduce the ratings data sparsity.The second phase analyses user actions in the considered social network scenario and incorporates the relative importance of users into the similarity computation for enhance the quality of recommendation.To evaluate the performance of the proposed model,a set of experiments on three real-world datasets are conducted.The results show that this model outperforms other methods,thus it can provide better performance than existing CF methods in mobile e-commerce environment.