The Role of Financial Indicators in the Prediction of Voluntary Carbon Disclosure: A Comparative Analysis with Machine Learning Methods

Carbon dioxide emissions and deforestation in the atmosphere since the industrial age are thought to be the leading causes of climate change. Many countries have developed policies to reduce greenhouse gas emissions and encourage firms to disclose and reduce their carbon emissions. Using machine learning methods, this study aims to reveal the potential financial predictors of carbon risk awareness, measured by the willingness to respond to the CDP survey of firms traded in Borsa Istanbul between 2016 and 2023. Furthermore, this study investigates whether machine learning algorithms can be used to improve the prediction of corporate carbon emissions for investors' risk analysis. As a result of the study, it is found that nonlinear and ensemble learning-based Random Forest and XGBosst algorithms can predict whether firms will make voluntary carbon disclosures with an accuracy of over 92%.