Forecasting Carbon Prices: A Literature Review

Carbon emissions trading is utilized by a growing number of states as a significant tool for addressing greenhouse gas emissions (GHG), global warming problem and the climate crisis. Accurate forecasting of carbon prices is essential for effective policy design and investment strategies in climate change mitigation. This review paper synthesizes recent advancements in carbon price forecasting models, examining time series methods, econometric approaches, and machine learning techniques, including neural networks and Long Short‐Term Memory (LSTM) models. By systematically presenting and comparing these methods, we identify key strengths and limitations, particularly highlighting the superior performance of advanced machine learning models in capturing nonlinear patterns and market complexities. Our review also explores innovative hybrid approaches, which address both short‐ and long‐term dynamics in carbon price trends.