Deep Learning Credit Risk Modeling
Forthcoming Journal of Fixed Income
Posted: 4 Aug 2020 Last revised: 11 Jun 2021
Date Written: July 1, 2020
Abstract
This paper demonstrates how deep learning can be used to price and calibrate models of credit risk. Deep neural networks can learn structural and reduced-form models with high degrees of accuracy. For complex credit risk models, whose closed-form solutions are not available, deep learning offers a conceptually simple and more efficient alternative solution. We propose an approach that combines deep learning with the unscented Kalman filter to calibrate credit risk models on historical data, which attains an in-sample R-squared of 98.5 percent for the reduced-form model and 95 percent for the structural model.
Keywords: Deep Learning, Machine Learning, Credit Risk Modeling, Default Risk, Sovereign Risk, Neural Networks
JEL Classification: G10, G12, G17
Suggested Citation: Suggested Citation