Firm-level climate change risk and adoption of ESG practices: a machine learning prediction

Abstract

Purpose

By combining the notion of prospect theory with advanced machine learning algorithms, this study aims to predict whether financial institutions (FIs) adopt a reactive stance when they perceive climate change as a risk, consequently leading to the adoption of environmental, social and governance (ESG) practices to avoid this risk. Prospect theory assumes that decision-makers react quickly when decisions are framed as a risk or threat rather than as an opportunity.

Design/methodology/approach

We used a sample of 168 FIs across 27 countries and seven regions over the period 2003–2020. To conduct our empirical investigation, we compared the prediction accuracy of various machine learning algorithms.

Findings

Our findings suggest that out of 12 machine learning algorithms, AdaBoost, Gradient Boosting and XGBoost have the most precision in predicting whether FIs react to climate change risk in adopting ESG practices. This study also tested the overall climate change risk and risks associated with physical, opportunity and regulatory shocks of climate change. We observed that risks associated with physical and regulatory shocks significantly impact the adoption of ESG practices, supporting prospect theory predictions.

Practical implications

The insights of this study provide important implications for policymakers. Specifically, policymakers must take into account the risk posed by climate change in the corporate decision-making process, as it directly influences a firm’s adoption of corporate actions (ESG practices).

Originality/value

To the best of our knowledge, this is the first study to investigate the firm-level climate change risk and adoption of ESG practices from a prospect theory perspective using novel machine learning algorithms.

Citation

Khan, M.H., Zein Alabdeen, Z. and Anupam, A. (2024), "Firm-level climate change risk and adoption of ESG practices: a machine learning prediction", Business Process Management Journal, Vol. 30 No. 6, pp. 1741-1763. https://doi.org/10.1108/BPMJ-05-2023-0401