Predictive Modeling for ESG Scores: A Comparative Analysis of Machine Learning Models on S&P 500 Firms' Sustainability Reports

View at publisher Summarise with VIRAT
Authors: Binitha Shree Gogineni, S Anirudh, Dwarakacherla Navya, Divya Sharma S.G.
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The need for efficient and standardized ESG score prediction by proposing a machine learning-based approach that automates ESG assessment using data from sustainability reports. Various regression models, including Ridge Regression, Linear Regression, and ensemble methods, are applied and evaluated based on metrics such as MAE, RMSE, and$\mathrm{R}^{2}$. Results indicate that Ridge Regression achieves the highest predictive accuracy, offering a reliable and scalable solution for data-driven ESG assessment to support sustainable investing.

Fields of Study & Subjects

Corporate Social Responsibility Reporting Sustainable Finance and Green Bonds Financial Distress and Bankruptcy Prediction

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
930–937
Publication date
21 January 2026
Language
EN