 Can Large Language Models forecast carbon price movements? Evidence from Chinese carbon marketsRui Chen, Haiqi Jiang, Tingyu Guo and Chenyou Fan Research in International Business and Finance, 2025, vol. 77, issue PB Abstract: This paper investigates the impact of Large Language Models (LLMs) on forecasting Chinese carbon prices. We introduce a novel two-stage forecasting framework integrating a Time-Series Model (TSM) and Large Language Models. Initially, we use historical data on Chinese Emission Allowance prices to train the TSM for preliminary predictions. LLMs then refine these predictions, which process a sequence of past and corresponding future prices as a chain of thought. Additionally, we utilize the LLM to analyze and categorize the sentiment of news headlines, generating market sentiment labels that enhance the LLM’s predictive accuracy. Our findings indicate that LLMs can improve TSM forecasts by 28–38 % across different regional markets. Furthermore, incorporating news sentiment labels into the LLM contributes an additional reduction in forecasting deviations, ranging from 3–4 %. Keywords: Carbon Price Forecasting; Large Language Models; Financial Sentiment Analysis; Machine Learning (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:riibaf:v:77:y:2025:i:pb:s0275531925002077 DOI: 10.1016/j.ribaf.2025.102951 Access Statistics for this article Research in International Business and Finance is currently edited by T. Lagoarde Segot More articles in Research in International Business and Finance from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.