Identifying profitability predictors in financial statements using explainable Artificial Intelligence

The interconnected nature of the economic variables influencing firm’s performance makes the prediction of a company’s earnings trend a challenging task. Existing methodologies often rely on simplistic models and financial ratios failing to capture the complexity of interacting influences. To address this gap this paper adopts 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. We propose adopting an eXplainable Artificial Intelligence method based on Game Theory to identify the most sensitive features and make the results more interpretable.