Deep Evidence Regression for Weibull targets

Ashish Dhiman

Keywords: Deep Learning, Probabilistic Methods, Computational Finance, Credit risk management

TL;DR: Extension of Deep Evidence Regression by Amini et al to Weibull target variables and application in credit risk domain

Abstract: 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.

Submission Number: 2320