Anmerkungen:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 22, 2023 erstellt
Beschreibung:
We estimate a large data panel of carbon emissions by US firms with a machine learning algorithm known as XGBoost. We estimate scope 1 carbon emissions of listed firms from 2002 to 2021. This data set has broad coverage of 4111 firms per year as compared to 1675 firms provided by data vendors. Based on this data set, we examine firms’ carbon risk pricing in the US equity market. The result shows that stocks of high-carbon firms earned higher returns before the Paris Agreement, whereas low-carbon firms outperform significantly in recent years. This contrasting phenomenon implies a positive shift in investors' ESG-related preferences and is more pronounced with our estimated data sample. Overall, this paper complements rather than challenges previous empirical research from both sides and provides researchers with a novel approach to understanding climate finance