Improved hybrid collaborative filtering algorithm based on K-means

Abstract

Due to the rapid development of e-commerce, both users and items are increasing, which leads to the problems of low efficiency and inaccurate recommendations when using collaborative filtering recommendation algorithms. In order to solve this problem better, this paper proposes an improved hybrid collaborative filtering algorithm based on K-Means. Firstly, use K-Means user clustering to divide users into different clusters according to the user’s behavioral habits, and then use item similarity to solve the sparseness of the scoring matrix. Finally, use collaborative filtering recommendation algorithm based on this to first determine which users belong to which clusters, calculating user similarities within a cluster. Experiments show that the algorithm proposed in this paper can avoid computing similarity on the entire data set to find the nearest neighbors, minimize the amount of computation, and improve the efficiency of the recommended algorithm.