UQ for Credit Risk Management: A deep evidence regression approach
This work addresses uncertainty quantification for credit risk management, which is crucial for financial institutions, but it is incremental as it extends an existing method to a specific domain.
The authors tackled the problem of quantifying uncertainty in credit risk predictions by applying Deep Evidence Regression to predict Loss Given Default, extending it to handle Weibull-generated variables and demonstrating results on simulated and real-world data.
Machine Learning has invariantly found its way into various Credit Risk applications. Due to the intrinsic nature of Credit Risk, quantifying the uncertainty of the predicted risk metrics is essential, and applying uncertainty-aware deep learning models to credit risk settings can be very helpful. In this work, we have explored the application of a scalable UQ-aware deep learning technique, Deep Evidence Regression and applied it to predicting Loss Given Default. We contribute to the literature by extending the Deep Evidence Regression methodology to learning target variables generated by a Weibull process and provide the relevant learning framework. We demonstrate the application of our approach to both simulated and real-world data.