基于信息融合的商业银行信用风险评估模型研究

The Assessment Model of Credit Risk of Commercial Bank

信用风险是我国商业银行运营过程中的主要风险,因此加强信用风险的有效评估至关重要。本文借鉴多传感器信息融合综合评价的优势,建立了基于BP神经网络、支持向量机和DS证据理论基础上的信用风险评估模型。通过采用国内某商业银行的数据,利用本模型、BP网络和支持向量机三者做了相应的验证,研究结果表明,该模型相对传统的BP网络和支持向量机的评估模型,能得出较优的评估结果。本文的研究结论对于丰富我国商业银行的信用风险评估体系和加强风险管理具有重要意义。

The effective assessment of credit risk is very important for commercial banks. Based on neural network, SVM and DS evidence theory and the preponderance of integrative assessment of information fusion, the paper builds an assessment model of credit risk and tests it with the data of a domestic commercial bank. The results show that newly-developed model can obtain better assessment compared with BP model and SVM model. This empirical result has important implication for the enriching credit risk assessment system and enhancing risk management.