Study on ESG Performance and Financial Distress Prediction of Listed Companies: Based on Logistic Regression and Artificial Neural Network

Abstract

A reliable financial distress prediction model is an effective means to prevent financial risks, and the selection of predictors is the key to improve the prediction accuracy of the model. To test whether the ESG performance of listed companies can be used to predict financial distress, two prediction models of logistic regression and artificial neural network were used to predict the financial distress of some listed companies from 2022 to 2024. The results show that the prediction accuracy of both models decreases after ESG ratings are added to the commonly used predictors. It proves that the ESG performance of listed companies cannot be used to predict financial distress, and this conclusion is valid after the robustness test.