Navajas Romero, Virginia , LÓPEZ MARTÍN, MARÍA DEL CARMEN, Gomez Requena, Natalia
No
Managing And Modelling Of Financial Risks
Proceedings Paper
Científica
01/01/2016
000429179000018
The level of default in financial institutions is a key piece of information in the activity of these organizations and reveals their level of risk. This in turn explains the growing attention given to variables of this kind, during the crisis of these last years. This paper presents a method to estimate the default rate using the non-linear model defined by neural networks; we use the most popular neural network model (the Multilayer Perceptron-MLP-) trained with the well-known back-propagation algorithm due to its simple architecture. We use this method with a database of credits to buy cars in three different experimental designs. The experimental results are not very good but it can be improved using other algorithms more complexes or all the independent variables, for example.
Level of default; financial institutions; neural networks; extreme learning machine