What question did this study set out to answer?

The aim is to predict the quality of ESG reporting across different global contexts using machine learning techniques.

Machine Learning Prediction of Environmental, Social and Governance Reporting Quality: A Global Cross‐Sectional Analysis

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial predicts ESG reporting quality using ML techniques in global corporations, suggesting new insights for investors and regulators.

The aim is to predict the quality of ESG reporting across different global contexts using machine learning techniques.
Cross-sectional sample of 5000 publicly listed companies across 50 countries for fiscal year 2022.
Developed and evaluated Random Forest and XGBoost models, alongside a panel regression benchmark.
Used financial performance metrics, corporate governance indicators, and institutional characteristics as predictors.
XGBoost achieved a test R2 of 0.78 compared to 0.62 for panel regression.
Identified firm size, governance score, and board independence as key predictors via SHAP analysis.
Board independence shows a threshold effect, with quality gains plateauing beyond 65%-70% independent directors.

Issah et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial predicts ESG reporting quality using ML techniques in global corporations, suggesting new insights for investors and regulators.