Bayesian regularized artificial neural networks for the estimation of the probability of default
Open Access
- 31 October 2019
- journal article
- research article
- Published by Taylor & Francis Ltd in Quantitative Finance
- Vol. 20 (2), 311-328
- https://doi.org/10.1080/14697688.2019.1633014
Abstract
Artificial neural networks (ANNs) have been extensively used for classification problems in many areas such as gene, text and image recognition. Although ANNs are popular also to estimate the probability of default in credit risk, they have drawbacks; a major one is their tendency to overfit the data. Here we propose an improved Bayesian regularization approach to train ANNs and compare it to the classical regularization that relies on the back-propagation algorithm for training feed-forward networks. We investigate different network architectures and test the classification accuracy on three data sets. Profitability, leverage and liquidity emerge as important financial default driver categories.Keywords
This publication has 21 references indexed in Scilit:
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012
- Modeling default risk with support vector machinesQuantitative Finance, 2011
- Bayesian Methods for Neural Networks and Related ModelsStatistical Science, 2004
- Bayesian approach for neural networks—review and case studiesNeural Networks, 2001
- Fast learning method for back-propagation neural network by evolutionary adaptation of learning ratesNeurocomputing, 1996
- Probabilistic neural networksNeural Networks, 1990
- Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedureJournal of Guidance, Control, and Dynamics, 1990
- Sampling-Based Approaches to Calculating Marginal DensitiesJournal of the American Statistical Association, 1990
- Algorithms for the Solution of the Nonlinear Least-Squares ProblemSIAM Journal on Numerical Analysis, 1978
- On the Pricing of Corporate Debt: The Risk Structure of Interest RatesThe Journal of Finance, 1974