Pré-Publication, Document De Travail Année : 2025

Machine Learning Approaches to Predicting Corporate Green, Social, and Sustainability Bond Issuance

Résumé

This study investigates the factors driving corporate green, social, sustainability, and sustainability-linked bond issuances (GSSS bonds) through an advanced machine learning framework that balances predictive accuracy and interpretability. By analyzing GSSS bonds issued by non-financial corporations across 51 countries from 2013 to 2024, the research highlights the effectiveness of Random Forest (RF) and XGBoost for prediction and Multinomial Logistic Regression (MLR) for model transparency. Feature importance analysis using SHAP values and Partial Dependence Plots (PDPs) identifies key drivers, including firm size, governance quality, ESG performance, and macroeconomic factors such as GDP per capita and inflation. The findings demonstrate RF's superior predictive accuracy, with larger firms and robust governance frameworks emerging as dominant influences on GSSS bond issuance.

Europe's leadership in sustainable finance further underscores the importance of strong regional frameworks. These insights provide practical guidance for issuers, investors, and policymakers, offering a roadmap to enhance sustainable finance strategies while contributing to global environmental and social objectives.

Fichier principal
Vignette du fichier
Machine Learning Approaches_Predicting Corporate GSSS_RBJ.pdf (1) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04906541 , version 1 (22-01-2025)

Identifiants

  • HAL Id : hal-04906541 , version 1

Citer

Riadh Ben Jelili. Machine Learning Approaches to Predicting Corporate Green, Social, and Sustainability Bond Issuance. 2025. ⟨hal-04906541⟩
0 Consultations
0 Téléchargements

Partager

More