Please use this identifier to cite or link to this item:
https://hdl.handle.net/10419/25207
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Härdle, Wolfgang Karl | en |
dc.contributor.author | Moro, Rouslan A. | en |
dc.contributor.author | Schäfer, Dorothea | en |
dc.date.accessioned | 2008-02-19 | - |
dc.date.accessioned | 2009-07-23T14:44:52Z | - |
dc.date.available | 2009-07-23T14:44:52Z | - |
dc.date.issued | 2007 | - |
dc.identifier.uri | http://hdl.handle.net/10419/25207 | - |
dc.description.abstract | This paper proposes a rating methodology that is based on a non-linear classification method, the support vector machine, and a non-parametric technique for mapping rating scores into probabilities of default. We give an introduction to underlying statistical models and represent the results of testing our approach on German Bundesbank data. In particular we discuss the selection of variables and give a comparison with more traditional approaches such as discriminant analysis and the logit regression. The results demonstrate that the SVM has clear advantages over these methods for all variables tested. | en |
dc.language.iso | eng | en |
dc.publisher | |aHumboldt University of Berlin, Collaborative Research Center 649 - Economic Risk |cBerlin | en |
dc.relation.ispartofseries | |aSFB 649 Discussion Paper |x2007,035 | en |
dc.subject.jel | C14 | en |
dc.subject.jel | G33 | en |
dc.subject.jel | C45 | en |
dc.subject.ddc | 330 | en |
dc.subject.keyword | Bankruptcy | en |
dc.subject.keyword | Company rating | en |
dc.subject.keyword | Default probability | en |
dc.subject.keyword | Support vector machines | en |
dc.subject.stw | Kreditwürdigkeit | en |
dc.subject.stw | Konkurs | en |
dc.subject.stw | Prognoseverfahren | en |
dc.subject.stw | Support Vector Machine | en |
dc.subject.stw | Theorie | en |
dc.subject.stw | Deutschland | en |
dc.title | Estimating probabilities of default with support vector machines | - |
dc.type | |aWorking Paper | en |
dc.identifier.ppn | 558556450 | en |
dc.rights | http://www.econstor.eu/dspace/Nutzungsbedingungen | en |
Files in This Item:
Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.