A Collaborative Filtering Recommendation Algorithm Based on User Information.

Abstract

As the rapid growth and wide application of Internet, the amount of information is increasing more quickly than people’s ability to process it. To help people to find useful information, personalized filtering technique emerges. Collaborative filtering is one successful personalized filtering technology, and is extensively used in many fields. But traditional collaborative filtering recommendation algorithm has the problem of sparsity, which will influence the efficiency of prediction, and collaborative filtering algorithms only consider users’ rating similarity. They do not consider users’ information similarity. Aiming at the problem of data sparsity for personalized filtering systems, a collaborative filtering recommendation algorithm based on user information is given. This method uses the user information similarity technology to fill the vacant ratings where necessary at first, and then uses collaborative filtering approach to produce recommendations.