于彤 李海东
摘 要: 我国商业银行信用风险管理不足,已经严重影响银行的发展,因而银行需要重视客户信用风险评估。分析了银行信用风险的成因及评估存在的问题,从企业的财务情况出发,建立了客户信用风险评估指标体系。随机选取了我国制造业的160个上市公司样本,包括36个ST企业和124个非ST企业,并基于三层BP神经网络对样本进行训练及仿真测试,研究发现BP神经网络适用于信用风险评估,且其准确性优于Logistic回归模型。最后,从银行、企业、政府三个角度出发,对我国商业银行信用风险管理提出了一些建议及对策。
关键词: 信用风险评估; 评估指标体系; 神经网络; 商业银行
中图分类号: TN911?34; F832.1 文献标识码: A 文章编号: 1004?373X(2014)10?0008?04
Abstract: The banks in China shouls pay more attention to the customer credit risk assessment because the commercial bank credit risk management in China is insufficient, which has seriously affected the development of banks. The formation cause of the bank credit risk and the problems existing in the assessment are analyzed. The customer credit risk assessment index system was established on the basis of financial situation of enterprises. The 160 samples in listed companies in Chinese manufacturing industry were selected randomly, including 36 ST companies and 144 non ST companies, and then tested based on three?layer BP neural network training. It is found in the research that the BP neural network is suitable for the credit risk assessment, and its accuracy is better than that of Logistic regression model. Some suggestions and countermeasures to the credit risk management of Chinese commercial banks are put forward.
Keywords: credit risk assessment; assessment index system; neural network; commercial bank
商业银行作为融资机构,为企业、政府及个人提供贷款是其最主要的服务之一,银行客户的存贷款利差是目前我国商业银行的主要收入来源[1],从而导致信用风险成为我国商业银行面临的最重要风险。
1 概 述
2012年末,我国商业银行不良贷款余额为4 928.5亿元,其中次级贷款为2 176.2亿元,可疑贷款为2 122.4亿元,损失贷款为630.0亿元,银监会强调了风险管理的重要性。
我国法律体系不完备、监管不到位、银行内部控制存在问题、信息不对称等原因,加剧了作为企业债权人银行的风险[2]。目前实行的紧缩性货币政策,使商业银行出现了“钱荒”现象,导致企业融资难。我国商业银行需要提高信用风险评估的技术和准确率,为信用等级较好的企业提供资金,实现资源优化配置。……