Credit Risk Evaluation Using least squares multiple criteria programming with L1 norm
Credit risk evaluation has been the major focus of financial and banking industry due to recent financial crises. Recent studies have revealed that emerging modern multiple criteria programming techniques are advantageous to statistical models for credit risk evaluation, such as MCP. In this study, we discuss the applications of the robust L_1 norm multiple criteria programming with multiple kernels to design a credit evaluation system, which can discriminate good creditors from bad ones. Differing from the standard multiple criteria programming (MCP), the L1-LS-MCP makes use of the 1-norm based object function and adopts the convex combinations of single feature basic kernels. As a result, only a linear programming problem needs to be resolved and thus it greatly reduces the computational costs. More importantly, it is a transparent model and the optimal feature subset can be obtained automatically. A real life credit dataset from a US commercial bank is used to demonstrate the good performance of the proposed model.
credit risk evaluation least squares multiple criteria programming least squares multiple riteria programming with L1 norm multiple criteria programming classification model
Wei Liwei Wang Bin
China national institute of standardization Beijing, China
国际会议
桂林
英文
240-243
2010-11-17（万方平台首次上网日期，不代表论文的发表时间）