Predicting Corporate ESG Scores from Financial Performance and Environmental Indicators: A Machine Learning Framework

Chouech, Olfa (2025): Predicting Corporate ESG Scores from Financial Performance and Environmental Indicators: A Machine Learning Framework. Published in: Journal of Cultural Analysis and Social Change , Vol. 10, No. 2589-1316 (2 December 2025): pp. 2042-2056.

Abstract

As investors, regulators, and the public increasingly emphasize sustainable investment amid growing climate concerns, the accurate prediction of Environmental, Social, and Governance (ESG) metrics has become a crucial complement to traditional assessment methods. This study analyzes 1,000 companies across nine industries and seven regions between 2015 and 2025 to predict overall ESG scores using key financial and environmental indicators. To ensure robust predictive performance, a diverse set of machine learning algorithms—including Linear Regression, Random Forests, and four boosting models (AdaBoost, LightGBM, XGBoost, and CatBoost)—was employed. To address potential bias in panel data, a panel-aware machine learning framework incorporating GroupKFold cross-validation was implemented. The results show that boosting algorithms consistently outperform traditional linear approaches in predicting ESG scores. Among them, CatBoost achieved the best overall performance, with the lowest RMSE (4.608), MAE (2.222), and MSE (21.234), and the highest R² (0.913), indicating strong predictive accuracy. Overall, this study presents an innovative and transferable framework for predicting ESG scores, thus contributing to both empirical research and quantitative modeling practices. Furthermore, it advances the sustainability field by providing a machine learning–based application that enables companies to predict their ESG scores in real time.

• Item Type: MPRA Paper
• English Title: A machine learning framework for predicting corporate ESG scores from financial performance and environmental indicators
• Language: English
• Keywords: ESG, Machine Learning, Boosting Algorithms, Sustainable Development, Predictive Modeling
• Subjects: O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O32 - Management of Technological Innovation and R&D; Q - Agricultural and Natural Resource Economics ; Environmental and Ecological Economics > Q5 - Environmental Economics > Q55 - Technological Innovation; Q - Agricultural and Natural Resource Economics ; Environmental and Ecological Economics > Q5 - Environmental Economics > Q56 - Environment and Development ; Environment and Trade ; Sustainability ; Environmental Accounts and Accounting ; Environmental Equity ; Population Growth

References

Albuquerque, R., Koskinen, Y., Yang, S., and Zhang, C. (2020). Resiliency of environmental and social stocks: An analysis of the exogenous COVID-19 market crash. Review of Corporate Finance Studies, 9(3), 593–621. https://doi.org/10.1093/rcfs/cfaa011

Aydoğmuş, M., Gülay, G., and Ergun, K. (2022). Impact of ESG performance on firm value and profitability. Borsa Istanbul Review, 22, S119–S127. https://doi.org/10.1016/j.bir.2022.11.006

Bancu, A. (2024). A meta-analysis of ESG disclosure and company’s economic performance. Proceedings of the International Conference on Business Excellence, 18(1), 2042–2056. https://doi.org/10.2478/picbe-2024-0173

Bourdeau, M., Zhai, X. Q., Nefzaoui, E., Guo, X., and Chatellier, P. (2019). Modeling and forecasting building energy consumption: A review of data-driven techniques. Sustainable Cities and Society, 48, 101533. https://doi.org/10.1016/j.scs.2019.101533

Broadstock, D. C., Chan, K., Cheng, L. T. W., and Wang, X. (2021). The role of ESG performance during times of financial crisis: Evidence from COVID-19 in China. Finance Research Letters, 38, 101716. https://doi.org/10.1016/j.frl.2020.101716

Chen, S., Song, Y., and Gao, P. (2023). Environmental, social, and governance (ESG) performance and financial outcomes: Analyzing the impact of ESG on financial performance. Journal of Environmental Management, 345, 118829. https://doi.org/10.1016/j.jenvman.2023.118829

Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.

D’Amato, V., D’Ecclesia, R., and Levantesi, S. (2021). Fundamental ratios as predictors of ESG scores: A machine learning approach. Decisions in Economics and Finance, 44, 1087–1110. https://doi.org/10.1007/s10203-021-00364-5

da Cunha, Í. G. F., Policarpo, R. V. S., de Oliveira, P. C. S., Abdala, E. C., and do Nascimento Rebelatto, D. A. (2025). A systematic review of ESG indicators and corporate performance: Proposal for a conceptual framework. Future Business Journal, 11(1), 106. https://doi.org/10.1186/s43093-025-00539-1

Díaz, V., Ibrushi, D., and Zhao, J. (2021). Reconsidering systematic factors during the COVID-19 pandemic: The rising importance of ESG. Finance Research Letters, 38, 101870. https://doi.org/10.1016/j.frl.2020.101870

Donaldson, T., and Preston, L. E. (1995). The stakeholder theory of the corporation: Concepts, evidence, and implications. Academy of Management Review, 20(1), 65–91. https://doi.org/10.5465/amr.1995.9503271992

Eccles, R. G., Ioannou, I., and Serafeim, G. (2014). The impact of corporate sustainability on organizational processes and performance. Management Science, 60(11), 2835–2857. https://doi.org/10.1287/mnsc.2014.1984

ESG Book (2023). Industry-relevant ESG disclosure levels remain low despite rise in sustainability reporting. https://www.esgbook.com/insights/press-releases/esg-disclosure-levels-remain-low-despite-rise-sustainability-reporting

Financial Reporting Council (2023). ESG data distribution and consumption. https://www.frc.org.uk/library/digital-reporting/esg/phase-2-esg-data-distribution-and-consumption

Freeman, R. E. (1984). Strategic management: A stakeholder approach. Boston: Pitman.

Freund, Y., and Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55, 119–139. https://doi.org/10.1006/jcss.1997.1504

Friede, G., Busch, T., and Bassen, A. (2015). ESG and financial performance: Aggregated evidence from more than 2000 empirical studies. Journal of Sustainable Finance and Investment, 5(4), 210–233. https://doi.org/10.1080/20430795.2015.1118917

Friedman, M. (1970). The social responsibility of business is to increase its profits. The New York Times Magazine. https://www.nytimes.com/1970/09/13/archives/a-friedman-doctrine-the-social-responsibility-of-business-is-to.html

García, F., González-Bueno, J., Guijarro, F., and Oliver, J. (2020). Forecasting the environmental, social, and governance rating of firms using corporate financial performance variables: A rough set approach. Sustainability, 12(8), 3324. https://doi.org/10.3390/su12083324

Giese, G., and Shah, D. (2025). ESG ratings in global equity markets: A long-term performance review. Journal of Impact and ESG Investing, 6(1). https://doi.org/10.3905/jesg.2025.1.132

Guerrero, S., and Viteri, J. P. (2025). What are environmental, social, and governance scores measuring? The role of outcome and impact indicators in ESG scores. Finance Research Letters, 72, 106529. https://doi.org/10.1016/j.frl.2024.106529

Ibrahim, Razib, N. H., and Rasel, I. H. (2025). The role of data analytics in enhancing ESG transparency in the corporate sector of Bangladesh. Global Journal of Engineering and Technology Advances, 22(1), 81–93. https://doi.org/10.30574/gjeta.2025.22.1.0245

Kartal, M. T., Kılıç Depren, S., Pata, U. K., Taşkın, D., and Şavlı, T. (2024). Modeling the link between ESG disclosures and scores: Evidence from the Borsa Istanbul Sustainability Index. Financial Innovation, 10(1), 80. https://doi.org/10.1186/s40854-024-00619-1

Ke, G., et al. (2017). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st Conference on Neural Information Processing Systems.

Langley, P., and Sage, S. (1994). Oblivious decision trees and abstract cases. AAAI-94 Workshop on Case-Based Reasoning, 113–117.

Linklater, R., Caprioli, S., Foschi, J., Crupi, R., and Sabatino, A. (2024). Deconstructing ESG scores: Investing at the category score level. Journal of Asset Management, 25(3), 222–244. https://doi.org/10.1057/s41260-024-00356-1

Lins, K. V., Servaes, H., and Tamayo, A. (2017). Social capital, trust, and firm performance: The value of corporate social responsibility during the financial crisis. Journal of Finance, 72(4), 1785–1824. https://doi.org/10.1111/jofi.12505

London Stock Exchange Group (2024). ESG scores. https://www.lseg.com/en/data-analytics/sustainable-finance/esg-scores

Nagassou, M., Mwangi, R. W., and Nyarige, E. (2023). A hybrid ensemble learning approach utilizing LightGBM and CatBoost for type-II diabetes prediction. Journal of Data Analysis and Information Processing, 11(4), 480–511. https://doi.org/10.4236/jdaip.2023.114025

Nofsinger, J., and Varma, A. (2014). Socially responsible funds and market crises. Journal of Banking and Finance, 48, 180–193. https://doi.org/10.1016/j.jbankfin.2013.12.016

Organisation for Economic Co-operation and Development (2025). Behind ESG ratings: Unpacking sustainability metrics. OECD Publishing. https://www.oecd.org

Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., and Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31.

Rozanski, M. (2023). Challenges of manual data collection for ESG reporting. https://osense.ai/resources/challenges-of-manual-data-collection-for-esg-reporting

Russell Investments (2023). 2023 manager ESG survey: Key insights. https://russellinvestments.com

Sariyer, G., Mangla, S. K., Chowdhury, S., Sozen, M. E., and Kazancoglu, Y. (2024). Predictive and prescriptive analytics for ESG performance evaluation. Journal of Business Research, 181, 114742. https://doi.org/10.1016/j.jbusres.2024.114742

Segal, M. (2024). Challenges of CSRD reporting requirements. ESG Today. https://www.esgtoday.com

Smith, A. (1776). An inquiry into the nature and causes of the wealth of nations. https://www.gutenberg.org/ebooks/3300

Suprihadi, E., and Danila, N. (2024). Forecasting ESG stock indices using a machine learning approach. Global Business Review. https://doi.org/10.1177/09721509241234033

Taskin, D., Sariyer, G., Acar, E., and Cagli, E. C. (2025). Do past ESG scores efficiently predict future ESG performance? Research in International Business and Finance, 74, 102706. https://doi.org/10.1016/j.ribaf.2024.102706

United Nations Global Compact (2000). The ten principles of the UN Global Compact. https://www.unglobalcompact.org

United Nations Global Compact (2004). Who cares wins. https://www.unglobalcompact.org/library/145

Wang, Y., Li, H., and Zhang, X. (2025). ESG rating system in sustainable finance: Challenges and suggestions. Advances in Economics, Management and Political Sciences, 3(2), 45–58. https://www.ewadirect.com

Yu, Z., Farooq, U., Alam, M. M., and Dai, J. (2024). How does ESG performance determine investment mix? Evidence from BRICS. Borsa Istanbul Review, 24(3), 520–529. https://doi.org/10.1016/j.bir.2024.02.007

Zeng, X., Zheng, L., and Cui, C. (2024). Leveraging AI and machine learning for ESG data analysis. ACE, 87. https://doi.org/10.54254/2755-2721/87/20241590

Zhao, L., Li, J., and Liu, Y. (2025). Are companies really awakening in ESG? International Journal of Disclosure and Governance, 22(1), 12–29. https://doi.org/10.1057/s41310-025-00309-z

Zou, Y., Shi, M., Chen, Z., Deng, Z., Lei, Z., Zeng, Z., and Zhou, W. (2025). ESGReveal: An LLM-based approach for extracting structured data from ESG reports. Journal of Cleaner Production, 489, 144572. https://doi.org/10.1016/j.jclepro.2024.144572