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.
@article{arxiv.1912.09764,
title = {An Artificial Intelligence approach to Shadow Rating},
author = {Angela Rita Provenzano and Daniele Trifirò and Nicola Jean and Giacomo Le Pera and Maurizio Spadaccino and Luca Massaron and Claudio Nordio},
journal= {arXiv preprint arXiv:1912.09764},
year = {2019}
}