Credit Scoring Models for a Tunisian Microfinance Institution: Comparison between Artificial Neural Network and Logistic Regression
Journal Title: Review of Economics & Finance - Year 2016, Vol 6, Issue 1
Abstract
This paper compares, for a microfinance institution, the performance of two individual classification models: Logistic Regression (Logit) and Multi-Layer Perceptron Neural Network (MLP), to evaluate the credit risk problem and discriminate good creditors from bad ones. Credit scoring systems are currently in common use by numerous financial institutions worldwide. However, credit scoring using a non-parametric statistical technique with the microfinance industry, is a relatively recent application. In Tunisia, no model which employs a non-parametric statistical technique has yet, as far as we know, been published. This lack is surprising since the implementation of credit scoring should contribute towards the efficiency of microfinance institutions, thereby improving their competitiveness. This paper builds a non-parametric credit scoring model based on the Multi-Layer perceptron approach (MLP) and benchmarks its performance against Logistic Regression (LR) techniques. Based on a sample of 300 borrowers from a Tunisian microfinance institution, the results reveal that Logistic Regression outperforms neural network models.
Authors and Affiliations
Aïda Kammoun, Imen Triki
Digital Divide and Income Inequality: A Spatial Analysis
A spatial quantile regression model, which can fully describe the distribution characteristics and spillover effects, is applied to explore the effect of digital divide on the income inequality. Firstly, the estimation r...
A “litmus test” of Deficit Sustainability: The Case of the Greek Budget Deficit
The paper applies three sustainability tests to the Greek budget deficit, which is known to be unsustainable, and can therefore be used to check the reliability of the three tests. Using three deficit definitions, i.e.,...
What Determines Union Density? A Political Economy Model of the Labor Market with Empirical Evidence in the Context of European Countries
In this investigation, a political economy model of the labor market is proposed, where unions offer their (old and new) affiliates the combinations between the average real wage level and the standard deviation of wages...
A Mixtured Localized Likelihood Method for GARCH Models with Multiple Change-points
This paper discusses GARCH models with multiple change-points and proposes a mixture localized likelihood method to estimate the piecewise constant GARCH parameters. The proposed method is statistically and computational...
Portfolio Optimization Using Multivariate t-Copulas with Conditionally Skewed Margins
Over the last few decades, copulas have consistently gained significance in finance research, due to their usefulness in risk modeling. However, the idea of implicitly representing dependencies between multiple assets in...