A scalable collaborative filtering algorithm based on localized preference
Liang Zhang, Bo Xiao, Jun Hai Guo, Chen Zhu · 2008
Collaborative filtering has been very successful in both research and applications. The K-nearest neighbor (KNN) method is a popular way for its realizations. Its key technique is to find k nearest neighbors for a given user to predict his interests. User-based clustering algorithms of collaborative filtering classify the users into some clusters and select top-N neighbors by using all items to compute similarity in one cluster. Collaborative filtering based on cluster has high scalability but low accuracy of prediction. In this paper we present a new approach to improve the accuracy and the scalability of collaborative filtering. Our approach partition the users, discovered the localized preference in each part and using the localized preference of users to select neighbors for prediction instead of using all items. We present empirical results which show that the method have better satisfactory accuracy and performance.