Machine Learning Predicts Voluntary Carbon Disclosure with 92% Accuracy

Strategic Insights -

Researchers at Yozgat Bozok Universitesi have found that machine learning algorithms can predict the willingness of firms to disclose carbon emissions with remarkable accuracy. The study, published in the Ekonomi, Politika & Finans Arastirmalari Dergisi journal, used financial indicators and machine learning methods to analyze the behavior of firms listed on the Borsa Istanbul between 2016 and 2023.

Key Takeaways:

  • The study aims to identify the potential financial determinants of carbon risk awareness among firms listed on the Borsa Istanbul between 2016 and 2023.
  • The researchers used machine learning methods, specifically Random Forest and XGBoost algorithms, to predict the willingness of firms to make voluntary carbon disclosures.
  • The findings reveal that specific financial ratios, such as the ratio of equity to total debt, the ratio of fixed assets to equity, and the ratio of long-term debt to total debt, significantly enhance the model's explainability within the XGBoost algorithm.
  • The study demonstrates that machine learning algorithms can improve investors' risk analysis in predicting corporate carbon emissions, contributing to the development of sustainable investment strategies.
  • The research highlights the potential of machine learning algorithms in improving climate change mitigation efforts by predicting the likelihood of firms to disclose carbon emissions.

Statistics:

  • The study found that machine learning algorithms can predict the willingness of firms to make voluntary carbon disclosures with an accuracy rate exceeding 92%.
  • The research analyzed financial data from 2016 to 2023, covering a period of seven years.
  • The study focused on firms listed on the Borsa Istanbul, providing a specific and relevant sample for the analysis.

Sources:

  • The Role of Financial Indicators in the Prediction of Voluntary Carbon Disclosure: A Comparative Analysis with Machine Learning Methods. Ekonomi, Politika & Finans Arastirmalari Dergisi, 2025,10(3):949-970.
  • doi-org.sdpl.idm.oclc.org/10.30784/epfad.1651693
  • Ekonomi ve Finansal Arastirmalar Dernegi (Publisher)
  • Yunus Emre Akdogan, YOZGAT BOZOK UNIVERSITESI, IKTISADI VE IDARI BILIMLER FAKULTESI, ISLETME BOLUMU (Contact Information)