Deep Learning Credit Risk Modeling

29 Pages Posted: 4 Aug 2020

See all articles by Gerardo Manzo

Gerardo Manzo

Kepos Capital

Xiao Qiao

Paraconic Technologies US Inc.

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

Manzo, Gerardo and Qiao, Xiao, Deep Learning Credit Risk Modeling (July 1, 2020). Available at SSRN: https://ssrn.com/abstract=3651379 or http://dx.doi.org/10.2139/ssrn.3651379

Gerardo Manzo (Contact Author)

Kepos Capital ( email )

620 Eighth Avenue
New York, NY 10018
United States

Xiao Qiao

Paraconic Technologies US Inc. ( email )

New York, NY
United States

HOME PAGE: http://sites.google.com/site/xiaoqiao10/

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
17
Abstract Views
149
PlumX Metrics