Pr\'evision du risque de cr\'edit : Une \'etude comparative entre l'Analyse Discriminante et l'Approche Neuronale
AbstractBanks are interested in evaluating the risk of the financial distress before giving out a loan. Many researchers proposed the use of models based on the Neural Networks in order to help the banker better make a decision. The objective of this paper is to explore a new practical way based on the Neural Networks that would help improve the capacity of the banker to predict the risk class of the companies asking for a loan. This work is motivated by the insufficiency of traditional prevision models. The sample consists of 86 Tunisian firms and 15 financial ratios are calculated, over the period from 2005 to 2007. The results are compared with those of discriminant analysis. They show that the neural networks technique is the best in term of predictability.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by arXiv.org in its series Papers with number 1311.4266.
Date of creation: Nov 2013
Date of revision:
Contact details of provider:
Web page: http://arxiv.org/
This paper has been announced in the following NEP Reports:
- NEP-ALL-2013-11-22 (All new papers)
- NEP-CMP-2013-11-22 (Computational Economics)
- NEP-RMG-2013-11-22 (Risk Management)
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.:
- Tam, KY, 1991. "Neural network models and the prediction of bank bankruptcy," Omega, Elsevier, Elsevier, vol. 19(5), pages 429-445.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (arXiv administrators).
If references are entirely missing, you can add them using this form.