Financial Forecasting Using ESG Indicators: A Random Forest-Based Predictive Approach
Resumo
Growing demand for sustainability transparency calls for quantitative tools to assess its financial impact. Despite limited models linking ESG and resource consumption to financial performance, this study integrates synthetic and real data from 1,086 companies (2015–2025), including Investics DARTS and Yahoo Finance sources, to improve data quality and representativeness. Using Random Forest and linear regression within a data mining framework, and after thorough preprocessing, we predicted corporate revenue. Results show environmental ESG scores and resource usage as strong predictors, with Random Forest reaching R2 ≈ 0.99. Complementary analysis reveals that higher market valuations correlate with better environmental performance, underscoring the financial importance of robust ESG metrics.
Palavras-chave:
Financial Forecasting, Machine Learning, Random Forest
Referências
de Franco, C. and Rebeiz, G. (2020a). Esg alpha: Do esg strategies outperform? EDHEC Working Paper.
de Franco, C. and Rebeiz, G. (2020b). From esg filters to machine learning: A new era of responsible investment. Journal of Sustainable Finance & Investment, 10(4):379–395.
Friede, G., Busch, T., and Bassen, A. (2015). Esg and financial performance: Aggregated evidence from more than 2000 empirical studies. Journal of Sustainable Finance & Investment, 5(4):210–233.
Gianfrate, G., Rubin, M., Ruzzi, D., and van Dijk, M. (2024). On the resilience of esg firms during the covid-19 crisis: evidence across countries and asset classes. Journal of International Business Studies, 55:1069–1084. Referência citada por EDHEC Vox :contentReference[oaicite:3]index=3.
Jiang, X. (2024). Explainable machine learning in esg scoring: Insights from shap analysis. Sustainability, 16(2):301.
Li, Y. (2025). Evaluating the financial impact of esg performance in developed markets: Insights from advanced machine learning and statistical models. Advances in Economics, Management and Political Sciences, 166:90–100.
Parashar, A., Verma, T., and Singh, R. (2024). Clustering esg scores and financial performance in renewable energy firms: A machine learning approach. Energy Economics and Sustainability Journal, 12(1):45–60.
de Franco, C. and Rebeiz, G. (2020b). From esg filters to machine learning: A new era of responsible investment. Journal of Sustainable Finance & Investment, 10(4):379–395.
Friede, G., Busch, T., and Bassen, A. (2015). Esg and financial performance: Aggregated evidence from more than 2000 empirical studies. Journal of Sustainable Finance & Investment, 5(4):210–233.
Gianfrate, G., Rubin, M., Ruzzi, D., and van Dijk, M. (2024). On the resilience of esg firms during the covid-19 crisis: evidence across countries and asset classes. Journal of International Business Studies, 55:1069–1084. Referência citada por EDHEC Vox :contentReference[oaicite:3]index=3.
Jiang, X. (2024). Explainable machine learning in esg scoring: Insights from shap analysis. Sustainability, 16(2):301.
Li, Y. (2025). Evaluating the financial impact of esg performance in developed markets: Insights from advanced machine learning and statistical models. Advances in Economics, Management and Political Sciences, 166:90–100.
Parashar, A., Verma, T., and Singh, R. (2024). Clustering esg scores and financial performance in renewable energy firms: A machine learning approach. Energy Economics and Sustainability Journal, 12(1):45–60.
Publicado
29/09/2025
Como Citar
SANTOS, Marco Antonio Sousa; DA SILVA, Adriano Rivolli; ORTONCELLI, André Roberto.
Financial Forecasting Using ESG Indicators: A Random Forest-Based Predictive Approach. In: BRAZILIAN E-SCIENCE WORKSHOP (BRESCI), 19. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 41-48.
ISSN 2763-8774.
DOI: https://doi.org/10.5753/bresci.2025.248122.
