本文以银行业金融机构大额授信风险及零售贷款违约风险数据 为基础, 从宏观经济环境、客户信 贷行为、企业经营水平三个维度出发,对客户风险预警的相关指标进行系统分析, 构建了企业客户风险预警指标体系, 并 利用统计学和数据挖掘方法, 从企业财务、企业信贷行为等客户数据信息 中挖掘出隐含在背后的客户风险特征. 在上述分析的基础上, 引入一种基于 Logit与SVM的混合预警模型. 该模型除了具有单个模型的良好基本性质, 还 能够充分捕捉和有效刻画影响因素对于客户违约的线性和非线性的复杂特征. 实 证结果表明, 新的模型具有更好的泛化能力, 对客户信贷风险具有较高的预警 准确率.
Abstract
In this study, based on the data of large credit risk and retail loan default risk of banking and financial institutions, we conducted a systematic analysis of indicators related to client risk early warning. Considering macroeconomic environment, customer credit behavior and enterprise management level, the indicator system of enterprise customer risk warning is established. Meanwhile, with the use of statistical methods as well as data mining skills, we find out the characteristics of customer risk implied in customer data concerning enterprise finance, credit behavior, and so on. According to the above analysis, a hybrid early warning model based on Logit and SVM is proposed, which has good basic properties of a single model and can effectively describe the linear and non-linear features of customer default influenced by different factors. Finally, the empirical results indicate that the new model has more generalization ability and higher accuracy of the credit risk early warning.
关键词
信用风险 /
Logit /
SVM /
混合预警模型
{{custom_keyword}} /
Key words
credit risk /
Logit /
SVM /
hybrid early warning model
{{custom_keyword}} /
中图分类号：
F832.33
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Fernando G, Vicente G, Francisco G. Credit risk management: A multicriteria approach to assess creditworthiness[J]. Mathematical and Computer Modelling, 2013, 57(7-8): 2009-2015.
[2] 郭保民. 论商业银行全面风险管理体系的构建[J]. 中南财经政法大学学 报, 2011(3): 80-85.Guo Baomin. Study of construction of ERM system in commercial bank[J]. Journal of Zhongnan University of Economics and Law, 2011(3): 80-85.
[3] Funda Y. Macroeconomic modelling of credit risk for banks[J]. Ocedia — Social and Behavioral Sciences, 2014, 109(8): 784-793.
[4] 刘#
[46] . 我国商业银行信用风险评估预警与缓释[D]. 合肥:中国科学技术大学, 2010.Liu Kun. Study on early warning and mitigation of credit risk of commercial banks: An angel of view of enterprise risk management[D]. Hefei: University of Science and Technology of China, 2010.
[5] 朱元倩, 苗雨峰. 关于系统性风险度量和预警的模型综述[J]. 国际金融研 究, 2012(1): 79-87.Zhu Yuanqian, Miao Yufeng. A summary of the model of system risk measurement and early warning[J]. Studies of International Finance, 2012(1): 79-87.
[6] 李志辉. 现代信用风险量化度量和管理研究[M]. 北京:中国金融出版社, 2001.Li Zhihui. Modern credit risk quantitative measurement and management[M]. Beijing: China Financial Publishing House, 2001.
[7] Mathieu B. Contagion effect on bond portfolio risk measures in a hybrid credit risk model[J]. Finance Research Letters, 2014, 11(2): 131-139.
[8] 刘迎春, 刘霄. 基于 GARCH 波动模型的 KMV 信用分析度量研究[J]. 东北财经 大学学报, 2011(3): 74-79.Liu Yingchun, Liu Xiao. The credit risk measurement research based on GARCH and KMV model[J]. Journal of Dongbei University of Finance and Economics, 2011(3): 74-79.
[9] 王春峰, 万海晖, 张维. 基于神经网络技术的商业银行信用风险评估[J]. 系统 工程理论与实践, 1999, 19(9): 24-32.Wang Chunfeng, Wan Haihui, Zhang Wei. Credit risk assessment in commercial banks using neural networks[J]. Systems Engineering — Theory & Practice, 1999, 19(9): 24-32.
[10] Adnan K. Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes[J]. Expert Systems with Applications, 2010, 37(9): 6233-6239.
[11] Yu L A, Yao X, Wang S Y, Credit risk evaluation using a weighted least squares SVM classifier with design of experiment for parameter selection[J]. Expert Systems with Applications, 2011, 38(12): 15392-15399.
[12] Paulius D, Gintautas G. Credit risk evaluation modeling using evolutionary linear SVM classifiers and sliding window approach[J]. Procedia Computer Science, 2012, 9: 1324-1333.
[13] So Y S, Ji W K, Decision tree-based technology credit scoring for start-up firms: Korean case[J]. Expert Systems with Applications, 2012, 39(4): 4007-4012.
[14] Tsai C F, Chen M L. Credit rating by hybrid machine learning techniques[J]. Appiled Soft Computing, 2010, 10(2): 374-380.
[15] Hua Z S, Wang Y, Xu X Y, et al. Predicting corporate financial distress based on integration of support vector machine and logistic regression[J]. Expert Systems with Applications, 2007, 33: 434-440.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(71271202); 国家数学与交叉科学中心全球经济监测预警与政策模拟仿真项目
{{custom_fund}}
PDF(721 KB)
