A New Method of Support Vector Machine for Class Imbalance Problem

In order to counterbalance the unfairness to rare class on using Support Vector Machine to credit assess for imbalanced dataset from commercial banks, an adjustment Method of the separating hyperplane is proposed in the paper. Based on Fisher discrimination, the projected class mean and variance are got by projecting two classes samples onto the normal vector of the separating hyperplane, then adjust the threshold of the hyperplane, according to the principle that error probability of two classes are equal. The proposed algorithm can compensate the ill-effect of tendency and improves the accuracy. Simulations on imbalanced data show that the feasibility and validity of the proposed method.