A Deep Learning Approach to Estimate Forward Default Intensities

39 Pages Posted: 4 Sep 2020 Last revised: 15 Sep 2020

Date Written: July 21, 2020


This paper proposes a machine learning approach to estimate physical forward default intensities. Default probabilities are computed using artificial neural networks to estimate the intensities of the inhomogeneous Poisson processes governing default process. The major contribution to previous literature is to allow the estimation of non-linear forward intensities by using neural networks instead of classical maximum likelihood estimation. The model specification allows an easy replication of previous literature using linear assumption and shows the improvement that can be achieved.

Keywords: Bankruptcy, Credit Risk, Default, Machine Learning, Neural Networks, Doubly Stochastic, Forward Poisson Intensities

JEL Classification: C22, C23, C53, C58, G33, G34

Suggested Citation

Divernois, Marc-Aurèle, A Deep Learning Approach to Estimate Forward Default Intensities (July 21, 2020). Swiss Finance Institute Research Paper No. 20-79, Available at SSRN: https://ssrn.com/abstract=3657019 or http://dx.doi.org/10.2139/ssrn.3657019

Marc-Aurèle Divernois (Contact Author)

EPFL ( email )

Quartier UNIL-Dorigny, Bâtiment Extranef, # 211
40, Bd du Pont-d'Arve
CH-1015 Lausanne, CH-6900

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics