Improved collaborative filtering approach based on user similarity combination

Abstract

Collaborative filtering is key technique of recommendation system. But traditional collaborative filtering methods are inefficient especially when the user-rating data is extremely sparse. To solve this problem, we propose an approach to compute the user similarity with the type of users-rating items in this paper, and then we develop a collaborative filtering algorithm based on this approach. Furthermore, we put forward an improved collaborative filtering algorithm based on user similarity combination, which combines the user similarity based on user-rating items and the user similarity based on the types of user-rating items. Last, we carry out an experiment with the classic Movielens data sets to evaluate the algorithm, and use MAE as the performance index. It shows that the collaborative filtering method based on the user similarity computed with types of user-rating items is more effective than the traditional method based on user similarity computed with user-rating items, and the collaborative filtering approach based on user similarity combination gets the best result.