Research on Ranking Support Vector machine and prospects

Learning to rank is designed to determine a ranking for the target objects according to some rule. Specifically, the problem about learning to rank is to learn a ranking function from a training set whose data has been ranked. It is most applied to the social sciences and information retrieval. Learning to rank is a hot issue in the field of information retrieval and machine learning at present. This paper analyses the process of Ranking Support Vector machine (RSVM) from a theoretical point of view from the classification and regression respectively, and sets up the two basic mathematical models about RSVM. The general introduction about RSVM in the application, training speed and generalization ability is also given. In the end, we come to a conclusion.