Cross-Sector Market Regime Forecasting with LLM-Augmented News Analysis
Mudarisov, T., State, R. V., Kraussl, Z. ORCID: 0000-0001-8718-4874 (2024). Cross-Sector Market Regime Forecasting with LLM-Augmented News Analysis. In: Proceedings of the 5th ACM International Conference on AI in Finance. ICAIF '24: 5th ACM International Conference on AI in Finance, 14-17 Nov 2024, Brooklyn, NY, USA. doi: 10.1145/3677052.3698642
Abstract
This paper investigates the utilization of news in predicting market regimes. The findings illustrate that employing an ensemble of multiple FinBERT models can outperform straightforward time-series prediction by 73% in accuracy and 110% in F1 score. The NLP models demonstrate strong performance across two different market-regime scenarios and show the ability to detect market shifts.
Publication Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Copyright © 2024 Owner/Author. This work is licensed under a Creative Commons Attribution International 4.0 License. |
Publisher Keywords: | Large Language Models, efficient market hypothesis, market-regimes |
Subjects: | H Social Sciences > HG Finance Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Departments: | Bayes Business School Bayes Business School > Finance |
SWORD Depositor: |
Available under License Creative Commons Attribution.
Download (925kB) | Preview