Explainable Artificial Intelligence for identifying profitability predictors in Financial Statements

TL;DR

This paper applies machine learning and explainability techniques to financial statement data to identify key profitability predictors, enhancing interpretability and regulatory compliance in financial analysis.

Contribution

It introduces an explainable AI approach based on Game Theory to interpret models predicting firm profitability from financial statements.

Findings

Identified key financial features influencing profitability

Compared multiple machine learning models for prediction accuracy

Enhanced model interpretability with explainability techniques

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.