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

Riadh Ben Jelili ()

Working Papers from HAL

Abstract: 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.

Keywords: Sustainable Bond Markets Machine Learning Governance and Sustainability Predictive Modeling; Sustainable Bond Markets; Machine Learning; Governance and Sustainability; Predictive Modeling (search for similar items in EconPapers)
Date: 2025-01-18
Note: View the original document on HAL open archive server: https://hal.science/hal-04906541v1
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hal.science/hal-04906541v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-04906541

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().