A Method to Solve Cold-Start Problem in Recommendation System based on Social Network Sub-community and Ontology Decision Model

Abstract

The paper presents a method to solve Cold-start problem in collaborative filtering recommendation system. Social sub-community is divided following analyzing exiting users’ history data and mining relationship between each other. Then ontology decision model is built in the basis of sub-community and users’ static information, which makes recommendation for new user based on his static ontology information. At last, the proposed method is used to recommenditems tonew users. In this paper, data simulation experiment is taken to test the technical method.