Clustering collaborative filtering recommendation algorithm of users based on time factor

Abstract

Collaborative filtering recommendation algorithm is the most widely used recommendation algorithm in recommendation systems. Based on the collaborative filtering recommendation algorithm, a time-based user clustering collaborative filtering recommendation algorithm is proposed. In this novel algorithm, all users and their interest changes are considered. There are three mainly improved steps in this novel algorithm. Firstly, the user rating time is added to increase the similarity between users when users are clustered. Secondly, in order to reduce the search space of similar users, only the nearest neighbor with a high similarity to the target user can be found in the cluster by adding the rating time. Finally, the traditional collaborative filtering recommendation algorithm is used to recommend the target users in the clustered data set. By using the MovieLens100K dataset, some experiments show the validity of the algorithm.