|
| |
| Manel Hamdi and Sami Mestiri |
| |
| ''Bankruptcy prediction for Tunisian firms : An application of semi-parametric logistic regression and neural networks approach'' |
| ( 2014, Vol. 34 No.1 ) |
| |
| |
| The paper uses two approaches, semi-parametric logistic regression model and artificial neural networks, to predict bankruptcy of Tunisian companies. A sample of 528 Tunisian firms for the period (1999-2006), was used to investigate the performance of these two approaches. The empirical results indicate that the quality of model prediction of the neural networks is better than the semi-parametric logistic regression model in terms of comparing the rates of misclassification and the area under curve (AUC) measures of the two proposed techniques. This research concludes that neural nets are a very powerful tool in bankruptcy prediction. |
| |
| |
| Keywords: Bankruptcy prediction, semi-parametric logistic regression, artificial neural networks |
JEL: C5 - Econometric Modeling: General
|
| |
| Manuscript Received : Dec 02 2013 | | Manuscript Accepted : Jan 30 2014 |
|
