Personal recommender system based on user interest community in social network model

Collaborative filtering is an effective method to help users find their interested items or services in e-commerce, such as Tmall, Amazon. The development of recommendation algorithms has been focused on how to provide accurate recommendation results. One of the big challenges on recommendation system is to make the best of outdated information sources. In order to solve this problem, an efficient time weighted collaborative filtering algorithm is proposed in this paper. In our presented recommendation algorithm, changes of interest over time are fully mined. Firstly, combining with rounding–forgetting function, a time weighted score matrix is constructed. The newfound matrix reflects many users’ interests. Then, the users and items with higher correlation are clustered into the same community according to differential equations. Stable same state values of users mean they own similar interests and then they are assigned into the same community. Finally, the real-time prediction results are obtained by dynamic similarity measurements. Effectiveness of our proposed algorithm is proven by extensive experimental evaluations which are based on different datasets. Diverse comparing results with several better methods are given to test the efficiency of our algorithm.