Personalized recommendation based on link prediction in dynamic super-networks

Abstract

Personalized recommendation is one of the most effective methods to solve the problem of information overloading. As many real existing systems in nature, a recommendation system can also be considered as a complex network system, so we can do personalized recommendation by using the link prediction method which is a new one in complex networks research area. In this paper, we present personalized recommendation method based on the link prediction in Super-networks. Firstly, we give several definitions such as a Super-network, a dynamic Super-network and a utility matrix etc. Secondly, we construct a personalized recommendation model based on these definitions. Thirdly, we define a similarity metric for users and some similarity criteria, put forward five link prediction related algorithms in dynamic Supernetworks and present our recommendation algorithms based on these link prediction algorithms. Finally, we apply our methods to classic datasets in order to evaluate the performance of our algorithms.