Rating Companies with Support Vector Machines
The goal of this work is to introduce one of the most successful among recently developed statistical techniques - the support vector machine (SVM) - to the field of corporate bankruptcy analysis. The main emphasis is done on implementing SVMs for analysing predictors in the form of financial ratios. A method is proposed of adapting SVMs to default probability estimation. A survey of practically and commercially applied methods is given. This work proves that support vector machines are capable of extracting useful information from financial data although extensive data sets are required in order to fully utilise their classification power.
|Date of creation:||2004|
|Date of revision:|
|Contact details of provider:|| Postal: Mohrenstraße 58, D-10117 Berlin|
Web page: http://www.diw.de/en
More information through EDIRC
References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Frydman, Halina & Altman, Edward I & Kao, Duen-Li, 1985. " Introducing Recursive Partitioning for Financial Classification: The Case of Financial Distress," Journal of Finance, American Finance Association, vol. 40(1), pages 269-91, March.
- Kar Yan Tam & Melody Y. Kiang, 1992. "Managerial Applications of Neural Networks: The Case of Bank Failure Predictions," Management Science, INFORMS, vol. 38(7), pages 926-947, July.
- Merton, Robert C., 1973.
"On the pricing of corporate debt: the risk structure of interest rates,"
684-73., Massachusetts Institute of Technology (MIT), Sloan School of Management.
- Merton, Robert C, 1974. "On the Pricing of Corporate Debt: The Risk Structure of Interest Rates," Journal of Finance, American Finance Association, vol. 29(2), pages 449-70, May.
- Dimitras, A. I. & Slowinski, R. & Susmaga, R. & Zopounidis, C., 1999. "Business failure prediction using rough sets," European Journal of Operational Research, Elsevier, vol. 114(2), pages 263-280, April.
When requesting a correction, please mention this item's handle: RePEc:diw:diwwpp:dp416. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Bibliothek)
If references are entirely missing, you can add them using this form.