Explainable Artificial Intelligence for identifying profitability predictors in Financial Statements
Abstract
The interconnected nature of the economic variables influencing a firm's performance makes the prediction of a company's earning trend a challenging task. Existing methodologies often rely on simplistic models and financial ratios failing to capture the complexity of interacting influences. In this paper, we apply Machine Learning techniques to raw financial statements data taken from AIDA, a Database comprising Italian listed companies' data from 2013 to 2022. We present a comparative study of different models and following the European AI regulations, we complement our analysis by applying explainability techniques to the proposed models. In particular, we propose adopting an eXplainable Artificial Intelligence method based on Game Theory to identify the most sensitive features and make the result more interpretable.
Cite
@article{arxiv.2501.17676,
title = {Explainable Artificial Intelligence for identifying profitability predictors in Financial Statements},
author = {Marco Piazza and Mauro Passacantando and Francesca Magli and Federica Doni and Andrea Amaduzzi and Enza Messina},
journal= {arXiv preprint arXiv:2501.17676},
year = {2025}
}
Comments
Short paper presented at Workshop on "Ai in Finance" at European Conference on Artificial Intelligence