KaydedilenlerDerginizi ekleyin

Dergiler / İşletme Bilimi Dergisi / 2026 / Cilt: 14 Sayı: 2

BIST Sürdürülebilirlik Endeksinde Yer Alan Firmaların ESG ve Çevresel Skorlarının Makine Öğrenmesi Yöntemleriyle Tahmini

Prediction of ESG and Environmental Scores of Firms Listed in the BIST Sustainability Index Using Machine Learning Methods

Mehmet Hanifi Ateş
İdil Koç
Sayfa
323–347
Yayın Tarihi
2026-06-23
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Uygulanan modeller, literatürdeki benzer çalışmalarla tutarlılık arz etmiş ve elde edilen sonuçlar, ESG skorlarının tahminlerinde yapay zekâ tabanlı yöntemlerin kullanılabilirliğini ortaya koymuştur.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Çevresel, sosyal ve kurumsal yönetişim (environmental, social, and governance-ESG) skorları, şirketlerin çevresel duyarlılığı, toplumsal sorumluluğu ve kurumsal yönetişim ilkelerine uyumu açısından önemli bir değerlendirme aracıdır.
📊
Temel Bulgular & Veri:Çalışmada, şirketlerin sürdürülebilirlik performanslarını değerlendirmek amacıyla ESG ve çevresel skorlarının tahmin edilmesine yönelik bir makine öğrenmesi yaklaşımı geliştirilmiştir. 2016-2023 dönemine ait BIST Sürdürülebilirlik endeksine dahil 95 şirketin Refinitiv veritabanından elde edilen ESG ve çevresel skorları ile şirketlerin sürdürülebilirlik ve entegre faaliyet raporları modelde kullanılmıştır.
💡
Sonuç & Katkı:Uygulanan modeller, literatürdeki benzer çalışmalarla tutarlılık arz etmiş ve elde edilen sonuçlar, ESG skorlarının tahminlerinde yapay zekâ tabanlı yöntemlerin kullanılabilirliğini ortaya koymuştur.
🔬Tür:Literatür & Derleme Çalışması
📍Kapsam:2016-2023 Verileri
⚙️Değişkenler:ESG Skorlaması · Çevresel Skorlama · Sürdürülebilir Finans

Özet

Çevresel, sosyal ve kurumsal yönetişim (environmental, social, and governance-ESG) skorları, şirketlerin çevresel duyarlılığı, toplumsal sorumluluğu ve kurumsal yönetişim ilkelerine uyumu açısından önemli bir değerlendirme aracıdır. ESG göstergelerine ilişkin veriler çoğunlukla yapılandırılmamış metin biçiminde yayımlandığından, sistematik analizleri hem teknik hem yöntemsel açılardan güçleşmektedir. Bu kapsamda, doğal dil işleme (NLP) tekniklerinin metin madenciliği ile birlikte kullanılması, yapılandırılmamış verilerin anlamlı özniteliklere dönüştürülmesinde önemli avantajlar sunmaktadır. Çalışmada, şirketlerin sürdürülebilirlik performanslarını değerlendirmek amacıyla ESG ve çevresel skorlarının tahmin edilmesine yönelik bir makine öğrenmesi yaklaşımı geliştirilmiştir. 2016-2023 dönemine ait BIST Sürdürülebilirlik endeksine dahil 95 şirketin Refinitiv veritabanından elde edilen ESG ve çevresel skorları ile şirketlerin sürdürülebilirlik ve entegre faaliyet raporları modelde kullanılmıştır. Metin tabanlı veriler üzerinde uygulanmak üzere toplam 6 farklı makine öğrenmesi algoritması denenmiş; Lojistik Regresyon, Support Vector Machines, GradientBoost ve LightGBM algoritmalarının, doğruluk ve F1 skoru gibi performans ölçütleri açısından en yüksek başarıyı gösterdiği saptanmıştır. Uygulanan modeller, literatürdeki benzer çalışmalarla tutarlılık arz etmiş ve elde edilen sonuçlar, ESG skorlarının tahminlerinde yapay zekâ tabanlı yöntemlerin kullanılabilirliğini ortaya koymuştur.

Abstract

Environmental, Social, and Governance (ESG) scores serve as an important assessment tool for evaluating companies’ environmental awareness, social responsibility, and adherence to corporate governance principles. Since data related to ESG indicators are mostly published in unstructured text format, conducting systematic analyses becomes challenging from both technical and methodological perspectives. In this context, the use of Natural Language Processing (NLP) techniques in combination with text mining offers significant advantages in transforming unstructured data into meaningful features. In this study, a machine learning approach was developed to predict ESG and environmental scores with the aim of evaluating companies’ sustainability performance. The model utilized ESG and environmental scores obtained from the Refinitiv database, along with the sustainability and integrated activity reports of 95 companies included in the BIST Sustainability Index for the 2016–2023 period. A total of six different machine learning algorithms were tested on the text-based data, and it was determined that the Logistic Regression, Support Vector Machines, GradientBoost and LightGBM algorithms achieved the highest performance in terms of evaluation metrics such as accuracy and F1 score. The applied models were found to be consistent with similar studies in the literature, and the results demonstrated the applicability of artificial intelligence-based methods in predicting ESG scores. .

🔖

Bu Makaleye Atıf Yap

Ateş, M. H., Koç, İ. (2026). BIST Sürdürülebilirlik Endeksinde Yer Alan Firmaların ESG ve Çevresel Skorlarının Makine Öğrenmesi Yöntemleriyle Tahmini. İşletme Bilimi Dergisi, Cilt: 14 Sayı: 2, 323–347. https://doi.org/10.22139/jobs.1748899

📄 Tam Metin PDF Okuyucu

↗Yeni Sekme

PDF belgesi yükleniyor...

Kaynakça (48)

  1. Antoncic, M. (2020). Uncovering hidden signals for sustainable investing using big data: Artificial intelligence, machine learning and natural language processing. Journal of Risk Management in Financial Institutions, 13(2), 106-113. https://doi.org/10.69554/CIKJ7477
  2. Bacha, S. ve Ajina, A. (2020). CSR performance and annual report readability: Evidence from France. Corporate Governance: The International Journal of Business in Society, 20(2), 201-215. https://doi.org/10.1108/CG-02-2019-0060
  3. Brundtland, G. H. (1987). Report of the World Commission on Environment and Development: Our Common Future. https://sustainabledevelopment.un.org/content/documents/5987our-common-future.pdf
  4. Castellano, R., Cini, F. ve Ferrari, A. (2024). Machine learning for ESG rating classification: An integrated replicable model with financial and systemic risk parameters. İçinde Mathematical and Statistical Methods for Actuarial Sciences and Finance (ss. 87-92). Springer.
  5. Caudron, E. (2022). Measuring ESG performance: A text mining approach. [Yayımlanmamış Yüksek Lisans Tezi, Université Catholique de Louvain].
  6. Chowdhury, M. A. F., Abdullah, M., Azad, M. A. K., Sulong, Z. ve Islam, M. N. (2023). Environmental, social and governance (ESG) rating prediction using machine learning approaches. Annals of Operations Research, 1-25. https://doi.org/10.1007/s10479-023-05633-7
  7. Clarkson, P. M., Ponn, J., Richardson, G. D., Rudzicz, F., Tsang, A. ve Wang, J. (2020). A textual analysis of US corporate social responsibility reports. Abacus, 56(1), 3-34.
  8. Clément, A., Robinot, É. ve Trespeuch, L. (2022). Improving ESG scores with sustainability concepts. Sustainability, 14(20). https://doi.org/10.3390/su142013154
  9. D’Amato, V., D’Ecclesia, R. ve Levantesi, S. (2021). Fundamental ratios as predictors of ESG scores: A machine learning approach. Decisions in Economics and Finance, 44(2), 1087-1110. https://doi.org/10.1007/s10203-021-00364-5
  10. Del Giudice, A. ve Rigamonti, S. (2020). Does audit improve the quality of esg scores? Evidence from corporate misconduct. Sustainability, 12(14), 5670. https://doi.org/10.3390/su12145670
  11. Depren, S. K., Taşkın, D. ve Ulussever, T. (2025). Uncovering the nexus between ESG reports and ESG scores across various liquidity levels: Evidence from publicly traded Turkish companies by machine learning algorithms. Journal of Sustainable Marketing, 1-20. https://doi.org/10.51300/JSE-2025-154
  12. Dumont, N. H. R. (2017). Sentiment analysis & natural language: Processing techniques for capital markets & disclosure. The Corporate Governance Advisor, 25(6), 16-23.
  13. Friede, G., Busch, T. ve Bassen, A. (2015). ESG and financial performance: Aggregated evidence from more than 2000 empirical studies. Journal of Sustainable Finance & Investment, 5(4), 210-233. https://doi.org/10.1080/20430795.2015.1118917
  14. Gao, S., Meng, F., Gu, Z., Liu, Z. ve Farrukh, M. (2021). Mapping and clustering analysis on environmental, social and governance field a bibliometric analysis using scopus. Sustainability, 13(13), 7304. https://doi.org/10.3390/su13137304
  15. Gupta, A., Dengre, V., Kheruwala, H. A. ve Shah, M. (2020). Comprehensive review of text-mining applications in finance. Financial Innovation, 6(1), 1-25. https://doi.org/10.1186/s40854-020-00205-1
  16. Heinberg, R. ve Lerch, D. (2010). What is sustainability, The post carbon reader, Post Carbon Institute. https://mycourses.aalto.fi/pluginfile.php/1159956/mod_page/content/9/Heinberg_WhatIsSustainability.pdf
  17. Henriksson, R., Livnat, J., Pfeifer, P. ve Stumpp, M. (2019). Integrating ESG in portfolio construction. The Journal of Portfolio Management, 45(4), 67-81. https://doi.org/10.3905/jpm.2019.45.4.067
  18. Hoverstadt, P. ve Bowling, D. (2005). Organisational viability as a factor in sustainable development of technology. International Journal of Technology Management & Sustainable Development, 4(2), 131-146. https://doi.org/10.1386/ijtm.4.2.131/1
  19. Hughes, A., Urban, M. A. ve Wójcik, D. (2021). Alternative ESG ratings: How technological innovation is reshaping sustainable investment. Sustainability, 13(6), 3551. https://doi.org/10.3390/su13063551
  20. Kartal, M. T., Kılıç Depren, S., Pata, U. K., Taşkın, D. ve Şavlı, T. (2024a). Modeling the link between environmental, social, and governance disclosures and scores: The case of publicly traded companies in the Borsa Istanbul Sustainability Index. Financial Innovation, 10(1), 80. https://doi.org/10.1186/s40854-024-00619-1
  21. Kartal, M. T., Taşkın, D., Shahbaz, M., Depren, S. K. ve Pata, U. K. (2024b). Effects of environment, social, and governance (ESG) disclosures on ESG scores: Investigating the role of corporate governance for publicly traded Turkish companies. Journal of Environmental Management, 368, 122205. https://doi.org/10.1016/j.jenvman.2024.122205
  22. Kiriu, T. ve Nozaki, M. (2020). A text mining model to evaluate firms’ ESG activities: An application for Japanese firms. Asia-Pacific Financial Markets, 27(4), 621-632. https://doi.org/10.1007/s10690-020-09309-1
  23. Kotsantonis, S. ve Serafeim, G. (2019). Four things no one will tell you about esg data. Journal of Applied Corporate Finance, 31(2), 50-58. https://doi.org/10.1111/jacf.12346
  24. Lee, J. ve Kim, M. (2023). ESG Information extraction with cross-sectoral and multi-source adaptation based on domain-tuned language models. Expert Systems with Applications, 221, 119726. https://doi.org/10.1016/j.eswa.2023.119726
  25. Lee, O., Joo, H., Choi, H. ve Cheon, M. (2022). Proposing an integrated approach to analyzing ESG data via machine learning and deep learning algorithms. Sustainability, 14(14), 8745. https://doi.org/10.3390/su14148745
  26. Li, T. -T., Wang, K., Sueyoshi, T. ve Wang, D. D. (2021). ESG: Research progress and future prospects. Sustainability, 13(21), 11663. https://doi.org/10.3390/su132111663
  27. Markoulidakis, I., Kopsiaftis, G., Rallis, I. ve Georgoulas, I. (2021). Multi-class confusion matrix reduction method and its application on net promoter score classification problem. Proceedings of the 14th Pervasive Technologies Related to Assistive Environments Conference, Corfu, Greece.
  28. Miklosik, A., Starchon, P. ve Hitka, M. (2021). Environmental sustainability disclosures in annual reports of asx industrials list companies. Environment, Development and Sustainability, 1-19. https://doi.org/10.1007/s10668-021-01338-8
  29. Ning, X., Yim, D. ve Khuntia, J. (2021). Online sustainability reporting and firm performance: Lessons learned from text mining. Sustainability, 13(3), 1069. https://doi.org/10.3390/su13031069
  30. Nugent, T., Stelea, N. ve Leidner, J. L. (2021). Detecting environmental, social and governance (ESG) topics using domain-specific language models and data augmentation. Flexible Query Answering Systems: 14th International Conference, FQAS, Bratislava, Slovakia içinde (ss. 157-169). Springer. https://doi.org/10.1007/978-3-030-86967-0_12
  31. Pagano, M. S., Sinclair, G. ve Yang, T. (2018). Understanding ESG ratings and esg indexes. Research Handbook of Finance and Sustainability, 339.
  32. Pasch, S. ve Ehnes, D. (2022). NLP for Responsible finance: Fine-tuning transformer-based models for ESG. 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.
  33. Refinitiv. (2023). Environmental, social and governance (ESG) scores from Refinitiv, https://www.lseg.com/content/dam/data-analytics/en_us/documents/methodology/lseg-esg-scores-methodology.pdf
  34. Ruberg, N. (2021). Bert goes sustainable: An NLP approach to ESG financing. [Yayımlanmamış Yüksek Lisans Tezi, University of Bologna].
  35. Shahi, A. M., Issac, B. ve Modapothala, J. R. (2014). Automatic analysis of corporate sustainability reports and intelligent scoring. International Journal of Computational Intelligence and Applications, 13(01), 1450006. https://doi.org/10.1142/S1469026814500060
  36. Shakil, M. H., Mahmood, N., Tasnia, M. ve Munim, Z. H. (2019). Do environmental, social and governance performance affect the financial performance of banks? A cross-country study of emerging market banks. Management of Environmental Quality: An International Journal, 30(3), 1331-1344. https://doi.org/10.1108/MEQ-08-2018-0155
  37. Svanberg, J., Ardeshiri, T., Samsten, I., Öhman, P., Neidermeyer, P. E., Rana, T., Semenova, N. ve Danielson, M. (2022). Corporate governance performance ratings with machine learning. Intelligent Systems in Accounting, Finance and Management, 29(1), 50-68. https://doi.org/10.1002/isaf.1505
  38. Székely, N. ve Vom Brocke, J. (2017). What can we learn from corporate sustainability reporting? Deriving propositions for research and practice from over 9,500 corporate sustainability reports published between 1999 and 2015 using topic modelling technique. PLOS One, 12(4), e0174807. https://doi.org/10.1371/journal.pone.0174807
  39. Şişman, M. E. ve Çankaya, S. (2021). Çevresel, sosyal ve kurumsal yönetişim (ESG) verilerinin firmaların finansal performansına etkisi: Hava yolu sektörü üzerine bir çalışma. Çukurova Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 25(1), 73-91. https://doi.org/10.51945/cuiibfd.880468
  40. Ting, I. W. K., Azizan, N. A., Bhaskaran, R. K. ve Sukumaran, S. K. (2019). Corporate social performance and firm performance: Comparative study among developed and emerging market firms. Sustainability, 12(1), 26. https://doi.org/10.3390/su12010026
  41. Taskin, D., Sariyer, G., Acar, E. ve 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
  42. UNPRI. (2005). Principles for Responsible Investment (PRI), United Nations Global Compact. https://www.unpri.org/
  43. Verbeeten, F. H. M., Gamerschlag, R. ve Möller, K. (2016). Are CSR disclosures relevant for investors? Empirical Evidence from Germany. Management Decision, 54(6), 1359-1382. https://doi.org/10.1108/MD-08-2015-0345
  44. Wong, C. ve Petroy, E. (2020). Rate the raters 2020: Investor survey and interview results. SustainAbility. https://www.sustainability.com/globalassets/sustainability.com/thinking/pdfs/sustainability-ratetheraters2020-report.pdf
  45. Yeprem, U. (2022). A Machine Learning-Based Approach to Corporate Social Performance Assessment. [Yayımlanmamış Yüksek Lisans Tezi, University of Guelph].
  46. Yıldız, B. ve Ağdeniz, Ş. (2023). Using text mining in financial reporting: To predict the companies’ corporate governance qualifications. Contemporary Studies of Risks in Emerging Technology, Part B içinde (ss. 147-168). Emerald Publishing Limited. https://doi.org/10.1108/978-1-80455-566-820231007
  47. Zaccone, M. C. ve Pedrini, M. (2020). ESG factor integration into private equity. Sustainability, 12(14), 5725. https://doi.org/10.3390/su12145725
  48. Zheng, A. (2015). Evaluating machine learning models: A beginner’s guide to key concepts and pitfalls. O’Reilly Media.