LA PREVENTION DU RISQUE DE DEFAUT DANS LES BANQUES TUNISIENNES. Analyse comparative entre les méthodes linéaires classiques et les méthodes de l'intelligence artificielle: les réseaux de neurones artificiels

Hamadi Matoussi and Aida Krichène Abdelmoula
Additional contact information
Aida Krichène Abdelmoula: UCAR - Université de Carthage (Tunisie)

Post-Print from HAL

Abstract: This paper addresses the question of default prediction of short term loans for a Tunisian commercial bank. We make a comparative analysis of three different statistical method of classification (artificial neural network and linear logistic regression with panel data). We use a database of 1435 files of credits granted to industrial Tunisian companies by a commercial bank in 2003, 2004, 2005 and 2006.The results show that the best prediction model is the multilayer neural network model and the best information set is the one combining accrual, cash-flow and collateral variables. We got a good classification rate of 97% in the training data set and 89.8% in the validation data set.

Keywords: Banking sector; scoring; logistic regression; Default risk Prediction; Neural network Models; Secteur bancaire scoring; régression logistique; panel; réseaux de neurones; la prévision du risque de défaut (search for similar items in EconPapers)
Date: 2010-05-10
Note: View the original document on HAL open archive server: https://hal.science/hal-00481087
References: Add references at CitEc
Citations:

Published in Crises et nouvelles problématiques de la Valeur, May 2010, Nice, France. pp.CD-ROM

Downloads: (external link)
https://hal.science/hal-00481087/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-00481087

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().