Collaborative Filtering Recommendation Algorithm Based on User Preferences

Abstract

The personalized recommendation technology provide people an effective method to solve the problem of information overload. Collaborative filtering is one of the key algorithm of recommendation technology, In this paper, the User-Movie (UM) model based on multilayer perceptron algorithm is a kind of item-based collaborative filtering recommendation algorithm. Therefore, the paper puts forward a new method to integrate item similarity in the UM model. Using Jaccard to find the similar items of current item, respectively. Experiments on the well-known datasets Epinions and Movielens show that the algorithm weighted by Jaccard in the case of sparse datasets and less neighbor achieves great improvement of prediction accuracy.