Deep Learning Credit Risk Modeling

This article 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 with no closed-form solutions available, deep learning offers a conceptually simple and more efficient alternative solution. This article proposes an approach that combines deep learning with the unscented Kalman filter to calibrate credit risk models based on historical data; this strategy attains an in-sample R-squared of 98.5% for the reduced-form model and 95% for the structural model. TOPICS:Credit risk management, big data/machine learning, quantitative methods, statistical methods Key Findings ▪ Neural networks can approximate solutions to credit risk models, precisely capturing the relationship between model inputs and credit spreads. ▪ Compared to standard techniques, the approximate solutions are more computationally efficient. ▪ Neural networks can be used to accurately calibrate structural and reduced-form models of credit risk.