考虑定性指标及误判损失的企业违约判别神经网络模型

中国管理科学 ›› 2006, Vol. ›› Issue (5): 104-108.

考虑定性指标及误判损失的企业违约判别神经网络模型

郭建伟, 唐春阳, 冯宗宪

西安交通大学, 西安, 710061

收稿日期:2005-09-13 修回日期:2006-10-08 出版日期:2006-10-28 发布日期:2012-03-07
基金资助:
国家自然科学基金项目(70171005);国家十五攻关项目(2001BA102A06-07-01)

Building Default Discriminating NN Model on Firm's Short-Term-Loan Data-Considering Qualitative Indexes and Misclassification Loss

GUO Jian-wei, TANG Chun-yang, FENG Zong-xian

Xi'an Jiaotong University, Xi'an 710061, China

Received:2005-09-13 Revised:2006-10-08 Online:2006-10-28 Published:2012-03-07

摘要/Abstract

摘要： 识别和度量企业的违约风险是银行风险管理中很重要的一项工作.目前企业违约判别模型离实际应用还具有一定差距,表现在:1)模型所使用的样本基本都是配对模式,不能代表整体样本;2)很少直接引入影响违约的定性指标,如行业,地区和规模;3)没有考虑到误判损失的非对称性.针对上述问题,本文应用前向BP网络针对某国有商业银行的2003年全部有效的短期贷款企业的财务数据,引入了定性指标,采用全样本进行训练,最后确定使误判损失最小的切割点,这样就得到优化的神经网络模型.

关键词: 神经网络, 定性指标, 误判损失

Abstract: To date,using models to predict whether firm's default is still a problem.It shows as follows: a. most models using pair wise pattern;b. lack of qualitative indexes that affect firm's default;c. asymmetric misclassification loss between normal firm and default firm.So,introducing qualitative indexes,using all samples and considering misclassification loss,this paper builds a neural network model on short-term-loan data.Though training,and testing,its performance is good.

Key words: neural network, qualitative indexes, misclassification loss

中图分类号:

F830.3

郭建伟, 唐春阳, 冯宗宪. 考虑定性指标及误判损失的企业违约判别神经网络模型[J]. 中国管理科学, 2006, (5): 104-108.

GUO Jian-wei, TANG Chun-yang, FENG Zong-xian. Building Default Discriminating NN Model on Firm's Short-Term-Loan Data-Considering Qualitative Indexes and Misclassification Loss[J]. Chinese Journal of Management Science, 2006, (5): 104-108.

参考文献

[1] 王春峰,万海晖,张维.商业银行信用风险评估及其实证研究[J].管理科学学报,1998,(1).
[2] 王春峰,万海辉,张维.组合预测在商业银行信用风险评估中的应用[J].管理科学学报,1999,(1).
[3] 管七海,冯宗宪.我国制造业企业短期贷款违约判别研究[J].经济科学,2004,(5).
[4] 唐春阳,冯宗宪.企业短期贷款违约预测Bayes模型构建[J].当代经济科学,2006,(1)
[5] 马若微,唐春阳.基于Fisher判别的企业短期贷款信用违约模型构建[J].系统工程,2005,(12)
[6] 张文彤.SPSS11.0统计分析教程(高级篇)[M].北京:希望电子出版社,2002.
[7] 管七海,冯宗宪.违约概率测度研究:文献综述与比较[J].世界经济,2004,(11).
[8] 飞思科技产品研发中心.MATLAB6.5辅助神经网络分析与设计[M].电子工业出版社,2003.
[9] 中国现代化报告课题组.中国现代化报告2001[R].http://www.modernization.com.cn,2005.
[10] Altman,E.I.Financial Ratios,Discriminant Analysis and the Prediction of Corporate Bankruptcy[J].Journal of Finance,1968:589-609.
[11] Altman,E.I,R.Haldeman and P.Narayanan.Zeta Analysis:A New Model to Identify Bankruptcy Risk of Corporation[J].Journal of Banking and Finance,1977,1:29-51.
[12] Altman E,Marco Geta.Corporate distress diagnosis:comparisons using linear discriminant analysis and neural networks (the Italian experience)[J].Journal of Banking and Finance,1994,18:505-529.
[13] Basel Committee on Banking Supervision.International Convergence of Capital Measurement and Capital Standards:A Revised Framework[S].2004,6.
[14] FreedmanA.A..survey of international banking[J].The economist,1993:1-37.
[15] Horrigan J.O..The Determinants of Long Term Credit Standing with Financial Ratios,Empirical Research in Accounting:Selected Studies[J].Supplement to Journal of Accounting Research,1966:44-62.
[16] Mark E.Zmijewski.Methodological Issues Related to the Estimation of Financial Distress Prediction Model[J].Journal of Accounting Research,1984,22:52-92.
[17] Ohlson J.S..Financial Ratios and the Probabilistic Prediction of Bankruptcy[J].Journal of Accounting Research,Spring 1980:109-130.