The Default Risk of Firms Examined with Smooth Support Vector Machines

SFB 649 Discussion Paper 2008-005

32 Pages Posted: 9 Jan 2017

See all articles by Wolfgang K. Härdle

Wolfgang K. Härdle

Humboldt University of Berlin - Institute for Statistics and Econometrics; Xiamen University - Wang Yanan Institute for Studies in Economics (WISE); Charles University; Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE)

Yuh-Jye Lee

National Taiwan University of Science and Technology

Dorothea Schaefer

German Institute for Economic Research (DIW Berlin); JIBS

Yi-Ren Yeh

National Taiwan University of Science and Technology

Date Written: December 3, 2007

Abstract

In the era of Basel II a powerful tool for bankruptcy prognosis is vital for banks. The tool must be precise but also easily adaptable to the bank's objections regarding the relation of false acceptances (Type I error) and false rejections (Type II error). We explore the suitability of Smooth Support Vector Machines (SSVM), and investigate how important factors such as selection of appropriate accounting ratios (predictors), length of training period and structure of the training sample influence the precision of prediction. Furthermore we show that oversampling can be employed to gear the tradeoff between error types. Finally, we illustrate graphically how different variants of SSVM can be used jointly to support the decision task of loan officers.

Keywords: Insolvency Prognosis, SVMs, Statistical Learning Theory, Non-parametric Classification

JEL Classification: G30, C14, G33, C45

Suggested Citation

Härdle, Wolfgang K. and Lee, Yuh-Jye and Schaefer, Dorothea and Yeh, Yi-Ren, The Default Risk of Firms Examined with Smooth Support Vector Machines (December 3, 2007). SFB 649 Discussion Paper 2008-005, Available at SSRN: https://ssrn.com/abstract=2894311 or http://dx.doi.org/10.2139/ssrn.2894311

Wolfgang K. Härdle (Contact Author)

Humboldt University of Berlin - Institute for Statistics and Econometrics ( email )

Unter den Linden 6
Berlin, D-10099
Germany

Xiamen University - Wang Yanan Institute for Studies in Economics (WISE) ( email )

A 307, Economics Building
Xiamen, Fujian 10246
China

Charles University ( email )

Celetná 13
Dept Math Physics
Praha 1, 116 36
Czech Republic

Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE)

Unter den Linden 6
Berlin, D-10099
Germany

Yuh-Jye Lee

National Taiwan University of Science and Technology ( email )

Keelung Road
Sec 43
Taipei
Taiwan

Dorothea Schaefer

German Institute for Economic Research (DIW Berlin) ( email )

Mohrenstraße 58
Berlin, 10117
Germany
+49 30 8978 9162 (Phone)
+49 30 8978 9104 (Fax)

JIBS ( email )

Jönköping, 55111
Sweden

Yi-Ren Yeh

National Taiwan University of Science and Technology ( email )

Keelung Road
Sec 43
Taipei
Taiwan

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
27
Abstract Views
308
PlumX Metrics