An Artificial Intelligence Approach to Shadow Rating
18 Pages Posted: 10 Jan 2020
Date Written: December 20, 2019
We analyse the effectiveness of modern deep learning techniques in predicting credit ratings over a universe of thousands of global corporate entities obligations when compared to most popular, traditional machine-learning approaches such as linear models and tree-based classifiers. Our results show a adequate accuracy over different rating classes when applying categorical embeddings to artificial neural networks (ANN) architectures.
Keywords: Rating Model, Shadow Rating, Artificial Intelligence, Machine Learning, Explainable AI
JEL Classification: C45, C55, G24
Suggested Citation: Suggested Citation