Can machine learning bring ESG ratings closer to small and medium-sized enterprises?

Abstract

Research background: Environmental, Social, and Governance (ESG) principles provide an important framework for companies to create value for stakeholders. Companies aim to enhance their performance in ESG as it has gained importance in investment analysis, with ESG ratings often used for this purpose. However, there is no objective way to calculate ESG scores, and small and medium-sized enterprises (SMEs) struggle to access ratings provided by score providers.

Purpose of the article: The main goal of this paper is to investigate whether the application of an artificial neural network (ANN) and feature selection techniques can make it possible to identify and prioritize the key features affecting companies’ ESG scores. Determining a set of key features from among the wide range of non-financial data reported by companies and then used by rating ESG score providers would benefit SMEs. It would allow them to report the most relevant non-financial data, that is considered in calculating ESG scores.

Methods: A feedforward ANN was employed to predict corporate ESG ratings based on environmental, social and governance data reported by companies to Refinitiv. Specifically, ESG data from 1,194 companies was analysed in this study across seven diverse sectors: Banking Services, Diversified Retail, Telecommunications Services, Metals and Mining, Oil and Gas, Software and IT Services, and Specialty Retailers. The companies represented 61 countries from six continents. The data encompassed the period from 2017 to 2021. Sectoral representation varied, with company numbers ranging from 74 to 260. A sequential forward feature selection process was next implemented to identify the minimal feature subset of 186 parameters used by Refinitiv for accurate ESG score prediction. The ANN model was trained iteratively to predict the ESG score, starting with an empty feature set and progressively adding features that most enhanced the model’s performance. The experiment was performed repeatedly for each sector.

Findings & value added: This paper proposes using machine learning (ML) to bring ESG ratings closer to SMEs. The study shows that ANN can accurately predict ESG scores using Refinitiv data, while retaining ESG ranking consistency. Furthermore, feature selection can infer ESG scores with acceptable accuracy using a minimal subset of key company attributes. Specifically, a neural network can accurately predict a company’s ESG score and determine its ranking using only around 13% of reported parameters. This approach may simplify access to ESG assessment for SMEs, allowing them to evaluate their performance with fewer parameters.

Keywords

ESG, neural network, feature selection, socially responsible investing, artificial intelligence, SMEs

References

1. Abhayawansa, S., & Tyagi, S. (2021). Sustainable investing: The black box of environmental, social, and governance (ESG) ratings. Journal of Wealth Management, 24(1), 49–54.
   View in Google Scholar
2. Ang, G., Guo, Z., & Lim, E. P. (2023). On predicting ESG ratings using dynamic company networks. ACM Transactions on Management Information Systems, 14(3), 27.
   View in Google Scholar
3. Ang, G., & Lim, E. P. (2024). Learning dynamic multimodal network slot concepts from the web for forecasting environmental, social and governance ratings. ACM Transactions on the Web, 18(3), 38.
   View in Google Scholar
4. Bax, K., Bonaccolto, G., & Paterlini, S. (2024). Spillovers in Europe: The role of ESG. Journal of Financial Stability, 72, 101221.
   View in Google Scholar
5. Berg, F., Kölbel, J. F., & Rigobon, R. (2022). Aggregate confusion: The divergence of ESG ratings. Review of Finance, 26(6), 1315–1344.
   View in Google Scholar
6. Bonini, S., & Swartz, S. (2014). Profits with purpose: How organizing for sustainability can benefit the bottom line. In McKinsey on sustainability & resource productivity (pp. 6–15). Mckinsey and Company.
   View in Google Scholar
7. Cesarone, F., Martino, M. L., Ricca, F., & Scozzari, A. (2024). Managing ESG ratings disagreement in sustainable portfolio selection. Computers & Operations Research, 170, 106766.
   View in Google Scholar
8. Chatterji, A. K., Durand, R., Levine, D. I., & Touboul, S. (2016). Do ratings of firms converge? Implications for managers, investors and strategy researchers. Strategic Management Journal, 37(8), 1597–1614.
   View in Google Scholar
9. Chatterji, A. K., & Levine, D. (2006). Breaking down the wall of codes: Evaluating non-financial performance measurement. California Management Review, 48(2), 29–51.
   View in Google Scholar
10. Chen, C. C., Tseng, Y. M., Kang, J., Lhuissier, A., Day, M. Y., Tu, T. T., & Chen, H. H. (2023). Multi-lingual ESG issue identification. In Proceedings of the fifth workshop on financial technology and natural language processing and the second multimodal AI for financial forecasting, (pp. 111–115). ACL Anthology.
    View in Google Scholar
11. Chen, M., & Mussalli, G. (2020). An integrated approach to quantitative ESG investing. Journal of Portfolio Management, 46(3), 65–74.
    View in Google Scholar
12. Choi, J. C., Chen, Q., & Lee, S. J. (2024). Predicting ESG ratings by machine learning and analyzing influencing factors by XAI. In ACM international conference proceeding series (pp. 120–125). ACM Digital Library.
    View in Google Scholar
13. Chowdhury, M. A. F., Abdullah, M., Azad, M. A. K., Sulong, Z., & Islam, M. N. (2023). Environmental, social and governance (ESG) rating prediction using machine learning approaches. Annals of Operations Research.
    View in Google Scholar
14. Christensen, D. M., Serafeim, G., & Sikochi, A. (2022). Why is corporate virtue in the eye of the beholder? The case of ESG ratings. Accounting Review, 97(1), 147–175.
    View in Google Scholar
15. Cini, F., & Ferrari, A. (2025). Towards the estimation of ESG ratings: A machine learning approach using balance sheet ratios. Research in International Business and Finance, 73.
    View in Google Scholar
16. D’Amato, V., D’Ecclesia, R., & Levantesi, S. (2021). Fundamental ratios as predictors of ESG scores: A machine learning approach. Decisions in Economics and Finance, 44(2), 1087–1110.
    View in Google Scholar
17. D’Amato, V., D’Ecclesia, R., & Levantesi, S. (2022). ESG score prediction through random forest algorithm. Computational Management Science, 19(2), 347–373.
    View in Google Scholar
18. Del Vitto, A., Marazzina, D., & Stocco, D. (2023). ESG ratings explainability through machine learning techniques. Annals of Operations Research.
    View in Google Scholar
19. Delmas, M. A., Etzion, D., & Nairn-Birch, N. (2013). Triangulating environmental performance: What do corporate social responsibility ratings really capture? Academy of Management Perspectives, 27(3), 255–267.
    View in Google Scholar
20. Dinh, T., Husmann, A., Melloni, G., Dinh, T., Husmann, A., & Melloni, G. (2023). Corporate sustainability reporting in Europe: A scoping review. Accounting in Europe, 20(1), 91–119.
    View in Google Scholar
21. Drempetic, S., Klein, C., & Zwergel, B. (2020). The influence of firm size on the ESG score: Corporate sustainability ratings under review. Journal of Business Ethics, 167(2), 333–360.
    View in Google Scholar
22. Dwivedi, D., Batra, S., & Pathak, Y. K. (2023). A machine learning based approach to identify key drivers for improving corporate’s ESG ratings. Journal of Law and Sustainable Development, 11(1), e0242.
    View in Google Scholar
23. Erhart, S. (2022). Take it with a pinch of salt ESG rating of stocks and stock indices. International Review of Financial Analysis, 83, 102308.
    View in Google Scholar
24. European Parliament. (2024). Directive (EU) 2024/1760 of the European Parliament and of the Council of 13 June 2024 on corporate sustainability due diligence and amending Directive (EU) 2019/1937 and Regulation (EU) 2023/2859.
    View in Google Scholar
25. European Parliament. (2022a). Corporate sustainability reporting directive.
    View in Google Scholar
26. European Parliament. (2022b). Sustainable economy: Parliament adopts new reporting rules for multinationals. Press Release.
    View in Google Scholar
27. Folqué, M., Escrig-Olmedo, E., & Corzo Santamaría, T. (2024). Integration of advanced SRI practices into the European asset management industry: A survey of drivers. SAGE Open, 14(1), 1–18.
    View in Google Scholar
28. Gamlath, M., Gunathilaka, C., Wijesinghe, A., Ahangama, S., Perera, I., & Sivaneasharajah, L. (2023). An integrated approach to ESG index construction with machine learning. Moratuwa Engineering Research Conference, MERCon, 252–257.
    View in Google Scholar
29. Gholami, A., Murray, P. A., & Sands, J. (2022). Environmental, social, governance & financial performance disclosure for large firms: Is this different for SME firms? Sustainability, 14(10), 6019.
    View in Google Scholar
30. Gjergji, R., Vena, L., Sciascia, S., & Cortesi, A. (2021). The effects of environmental, social and governance disclosure on the cost of capital in small and medium enterprises: The role of family business status. Business Strategy and the Environment, 30(1), 683–693.
    View in Google Scholar
31. González-Pozo, R., Arenas-Parra, M., Quiroga-García, R., & Bilbao-Terol, A. (2024). A proposal for refining the ESG methodology used by rating agencies. International Transactions in Operational Research.
    View in Google Scholar
32. GSIA. (2023). Global sustainable investment review 2022.
    View in Google Scholar
33. Gupta, A., Sharma, U., & Gupta, S. K. (2021). The role of ESG in sustainable development: An analysis through the lens of machine learning. In 2021 IEEE international humanitarian technology conference, IHTC 2021, (pp. 1–5). IEEE.
    View in Google Scholar
34. HKEx. (2015). Consultation paper. Review of the environmental, social and governance reporting guide. Hong Kong Exchanges and Clearing Limited.
    View in Google Scholar
35. Inampudi, K., & Macpherson, M. (2021). The impact of AI on environmental, social and governance (ESG) investing: Implications for the investment value chain. In S. Chishti, I. Bartoletti, A. Leslie, & S. M. Millie (Eds.). The AI book: The artificial intelligence handbook for investors, entrepreneurs and FinTech visionaries (pp. 129–131). John Wiley & Sons, Ltd.
    View in Google Scholar
36. Kingma, D. P., & Ba, J. L. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd international conference on learning representations (ICLR 2015). DBLP. Computer Science Bibiography.
    View in Google Scholar
37. Koehler, D., & Hespenheide, E. (2013). Finding the value in environmental, social and governance performance. Deloitte Review, 12, 97–111.
    View in Google Scholar
38. Lee, H., Jung, H. S., Park, H., & Kim, J. H. (2024). CORRECT? CORECT!: Classification of ESG ratings with earnings call transcript. KSII Transactions on Internet and Information Systems, 18(4), 1090–1100.
    View in Google Scholar
39. Lee, O., Joo, H., Choi, H., & Cheon, M. (2022). Proposing an integrated approach to analyzing ESG data via machine learning and deep learning algorithms. Sustainability, 14(14), 8745.
    View in Google Scholar
40. Li, X., Saat, M. M., Khatib, S. F. A., & Liu, Y. (2024). Sustainable development and firm value: How ESG performance shapes corporate success—a systematic literature review. Business Strategy & Development, 7(4), e70026.
    View in Google Scholar
41. Liang, L., Liu, B., Su, Z., & Cai, X. (2024). Forecasting corporate financial performance with deep learning and interpretable ALE method: Evidence from China. Journal of Forecasting, 43(7), 2540–2571.
    View in Google Scholar
42. Lin, H. Y., & Hsu, B. W. (2023). Empirical study of ESG score prediction through machine learning - A case of non-financial companies in Taiwan. Sustainability, 15(19), 14106.
    View in Google Scholar
43. Lopez, C., Contreras, O., & Bendix, J. (2020). ESG ratings: The road ahead. SSRN Electronic Journal.
    View in Google Scholar
44. Möller, V., Koehler, D. A., & Stubenrauch, I. (2015). Finding the value in environmental, social and governance performance. In L. O’Riordan, P. Zmuda, & S. Heinemann (Eds.). New perspectives on corporate social responsibility: Locating the missing link (pp. 275–283). Wiesbaden: Springer Gabler.
    View in Google Scholar
45. Momparler, A., Carmona, P., & Climent, F. (2025). Catalyzing sustainable investment: Revealing ESG power in predicting fund performance with machine learning. Computational Economics, 65, 1617–1642.
    View in Google Scholar
46. Ozkan, S., Romagnoli, S., & Rossi, P. (2023). A novel approach to rating SMEs’ environmental performance: Bridging the ESG gap. Ecological Indicators, 157, 111151.
    View in Google Scholar
47. Pérez, L., Hunt, D. V., Samandari, H., Nuttall, R., & Biniek, K. (2022). Does ESG really matter - and why? Retrieved from https://www.mckinsey.com/capabilities/sustainability/our-insights/does-esg-rea lly-matter-and-why.
    View in Google Scholar
48. Postiglione, M., Carini, C., & Falini, A. (2024). ESG and firm value: A hybrid literature review on cost of capital implications from Scopus database. Corporate Social Responsibility and Environmental Management, 31(6), 6457–6480.
    View in Google Scholar
49. Rubino, M., Mastrorocco, I., & Garegnani, G. M. (2024). The influence of market and institutional factors on ESG rating disagreement. Corporate Social Responsibility and Environmental Management, 31(5), 3916–3926.
    View in Google Scholar
50. Sahut, J.-M., & Pasquini-Descomps, H. (2015). ESG impact on market performance of firms: International evidence. Management International, 19(2), 40–63.
    View in Google Scholar
51. Sharma, U., Gupta, A., & Gupta, S. K. (2022). The pertinence of incorporating ESG ratings to make investment decisions: A quantitative analysis using machine learning. Journal of Sustainable Finance and Investment, 14(1), 184–198.
    View in Google Scholar
52. Shi, J., Zhang, C., Wen, J., Zhang, Z., & Wu, T. (2024). Research on improving the key indicators of enterprise ESG rating. Procedia Computer Science, 242, 912–919.
    View in Google Scholar
53. SSE. (2024). Sustainable stock exchange initiative, stock exchange database. https://sseinitiative.org/exchanges-filter-search.
    View in Google Scholar
54. Svanberg, J., Ardeshiri, T., Samsten, I., Öhman, P., Neidermeyer, P. E., Rana, T., Maisano, F., & Danielson, M. (2023). Must social performance ratings be idiosyncratic? An exploration of social performance ratings with predictive validity. Sustainability Accounting, Management and Policy Journal, 14(7), 313–348.
    View in Google Scholar
55. Svanberg, J., Ardeshiri, T., Samsten, I., Öhman, P., Neidermeyer, P. E., Rana, T., Semenova, N., & Danielson, M. (2022a). Corporate governance performance ratings with machine learning. Intelligent Systems in Accounting, Finance and Management, 29(1), 50–68.
    View in Google Scholar
56. Svanberg, J., Ardeshiri, T., Samsten, I., Öhman, P., Rana, T., & Danielson, M. (2022b). Prediction of environmental controversies and development of a corporate environmental performance rating methodology. Journal of Cleaner Production, 344, 130979.
    View in Google Scholar
57. Telukdarie, A., Mahure, H., & Sishi, M. (2024). The digitization of ESG matrix. Procedia Computer Science, 239, 808–815.
    View in Google Scholar
58. Teoh, T. T., Heng, Q. K., Chia, J., Shie, J. M., Liaw, S. W., Yang, M., & Nguwi, Y. Y. (2019). Machine learning-based corporate social responsibility prediction. In Proceedings of the IEEE 2019 9th international conference on cybernetics and intelligent systems and robotics, automation and mechatronics, CIS and RAM 2019, (pp. 501–505). IEEE.
    View in Google Scholar
59. Trumpp, C., Endrikat, J., Zopf, C., & Guenther, E. (2015). Definition, conceptualization, and measurement of corporate environmental performance: A critical examination of a multidimensional construct. Journal of Business Ethics, 126(2), 185–204.
    View in Google Scholar
60. Tseng, Y. M., Chen, C. C., Huang, H. H., & Chen, H. H. (2023). DynamicESG: A dataset for dynamically unearthing ESG ratings from news articles. In International conference on information and knowledge management, proceedings (pp. 5412–5416). ACM Digital Library.
    View in Google Scholar
61. Twinamatsiko, E., & Kumar, D. (2022). Incorporating ESG in decision making for responsible and sustainable investments using machine learning. In Proceedings of the international conference on electronics and renewable systems, ICEARS 2022, (pp. 1328–1334). IEEE.
    View in Google Scholar
62. Vu, T. N., Lehkonen, H., Junttila, J. P., & Lucey, B. (2025). ESG investment performance and global attention to sustainability. North American Journal of Economics and Finance, 75(Part A), 102287.
    View in Google Scholar
63. Xue, Q., Jin, Y., & Zhang, C. (2024). ESG rating results and corporate total factor productivity. International Review of Financial Analysis, 95(Part A), 103381.
    View in Google Scholar
64. Yoo, S., & Managi, S. (2022). Disclosure or action: Evaluating ESG behavior towards financial performance. Finance Research Letters, 44, 102–108.
    View in Google Scholar
65. Zhang, A. Y., & Zhang, J. H. (2023). Renovation in environmental, social and governance (ESG) research: The application of machine learning. Asian Review of Accounting, 32(4), 554–572.
    View in Google Scholar
66. Zhang, C., Hao, D., Gao, L., Xia, F., & Zhang, L. (2024a). Do ESG ratings improve capital market trading activities? International Review of Economics and Finance, 93, 195–210.
    View in Google Scholar
67. Zhang, C., Farooq, U., Jamali, D., & Alam, M. M. (2024b). The role of ESG performance in the nexus between economic policy uncertainty and corporate investment. Research in International Business and Finance, 70, 102358.
    View in Google Scholar