Abstract:

The article describes the main rationale for banks' involvement in ESG issues, assesses the usefulness of selected machine learning and explainable artificial intelligence tools in determining the relevance of ESG parameters, and identifies the benefits, challenges and uncertainties of using machine learning tools in banks' ESG self-assessment process. The research included conducting an experiment using the XGBoost algorithm and the SHAP method. The subjects of the study were 52 European banks. ESG data covering 2018-2022 was obtained from Refinitive (now LSEG Data & Analytics). The research shows that the SHAP Method and XGBoost algorithm can be used to assess the importance of ESG indicators and identify those that have a significant impact on the ESG score of banks.