Cookies?
Library Header Image
LSE Research Online LSE Library Services

Bayesian regularized artificial neural networks for the estimation of the probability of default

Sariev, Eduard and Germano, Guido (2019) Bayesian regularized artificial neural networks for the estimation of the probability of default. Quantitative Finance. ISSN 1469-7688 (In Press)

[img] Text (Bayesian regularised artificial neural networks) - Accepted Version
Pending embargo until 1 January 2100.

Download (704kB) | Request a copy

Abstract

Artificial neural networks (ANN) have been extensively used for classification problems in many areas such as gene, text and image recognition. Although ANN 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 ANN 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.

Item Type: Article
Official URL: https://www.tandfonline.com/toc/rquf20/current
Additional Information: © 2019 Informa UK
Divisions: Systemic Risk Centre
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
H Social Sciences > HA Statistics
H Social Sciences > HG Finance
Date Deposited: 14 Jun 2019 11:33
Last Modified: 20 Jul 2019 23:10
URI: http://eprints.lse.ac.uk/id/eprint/101029

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics