Research of evaluating credit-risk in power enterprise based on SVM and VIKOR method

Some clients are in arrears with a great amount of electricity charges in operation of power system, which has seriously hindered the healthy development of electric industry. Evaluation of clients¿ credit is an important problem of management in power supply enterprises.Considering the training time and the accuracy, a new algorithm based on Support Vector Machine (SVM) and VIKOR method is adopted to solve this problem. Support Vector Machine (SVM) was proposed to solve the small sample learning problem. VIKOR method was developed to solve decision problems with conflicting and with different units criteria.Finally, an application example has been given to test the feasibility and effectiveness of the proposed method.