用支持向量机(SVM)构建企业破产预测模型  

An Application of Support Vector Machines in Bankruptcy Prediction Model

作　　者：杨毓[1] 蒙肖莲[2] 

机构地区：[1]华中科技大学,湖北武汉430074 [2]南京理工大学,江苏南京210094

出　　处：《金融研究》2006年第10期65-75,共11页Journal of Financial Research

基　　金：国家自然科学基金资助项目(70271030)"企业客户关系管理中服务机理与支持平台的研究"。

摘　　要：本文考察支持向量机SVM(Support Vector Machines)在商业银行构建企业破产预测模型中的作用。由于SVM能够使用小样本捕获特征空间的几何特征并抽取出最优解,因此对于企业破产预测问题,使用SVM方法构建的分类机的性能比倒传递神经网络模型(BPN)方法构建的分类机的性能要好。本文同时考察了取不同参数值时SVM模型性能的变化。此外,本文考察和总结了与BPN相比,SVM算法的几个优越点。研究结果表明,当训练集的规模变小时,SVM的精确性和推广性能优于BPN．This paper studies the effectiveness of applying support vector machines （SVM） to bankruptcy prediction problem in commercial banks. Since SVM can capture geometric characteristics of feature space and capable of extracting the optimal solution with the small training set size, the classifier of SVM approach outperforms BPN to the problem of corporate bankruptcy prediction. The effect of the variability in performance with respect to various values of paran^ters in SVM is also examined. In addition ,the paper summarizes several superior points of the SVM algorithm compared with BPN. The results demonstrate that the accuracy and generalization performance of SVM is better than that of BPN as the training set size gets smaller.

关 键 词：企业破产预测 支持向量机 商业银行 

分 类 号：F271[经济管理—企业管理] F224[经济管理—国民经济]