Enhancing stock timing predictions based on multimodal architecture: Leveraging large language models (LLMs) for text quality improvement
PLOS One · 18.06.2025 · 20 (6) · e0326034
DOI: 10.1371/journal.pone.0326034 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.06.2025. Verfasst von Mingming Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Pharmacy, Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, China. Hauptthemen laut MEDLINE: Investments, Language, Quality Improvement, Models, Economic. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study aims to enhance stock timing predictions by leveraging large language models (LLMs), specifically GPT-4, to filter and analyze online investor comment data. Recognizing challenges such as variable comment quality, redundancy, and authenticity issues, we propose a multimodal architecture that integrates filtered comment data with stock price dynamics and technical indicators. Using data from nine Chinese banks, we compare four filtering models and demonstrate that employing GPT-4 significantly improves financial metrics like profit-loss ratio, win rate, and excess return rate. The multimodal architecture outperforms baseline models by effectively preprocessing comment data and combining it with quantitative financial data. While focused on Chinese banks, the approach can be adapted to broader markets by modifying the prompts of large language models. Our findings highlight the potential of LLMs in financial forecasting and provide more reliable decision support for investors.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Academy of Pharmacy, Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, China.
- Institute of Population Health, Faculty of Health & Life Sciences, Waterhouse Building, University of Liverpool, Liverpool, United Kingdom.
- Faculty of Computing and Data Sciences, Boston University, Boston, Massachusetts, United States of America.
ORCID-Profile: Tenglong Li
Zitieren
APA
Chen, M., Tang, Y., Qi, Q., Dai, H., Lin, Y., Ling, C., & Li, T. (2025). Enhancing stock timing predictions based on multimodal architecture: Leveraging large language models (LLMs) for text quality improvement. PLOS One, 20(6), e0326034. https://doi.org/10.1371/journal.pone.0326034
Vancouver
Chen M, Tang Y, Qi Q, Dai H, Lin Y, Ling C, et al. Enhancing stock timing predictions based on multimodal architecture: Leveraging large language models (LLMs) for text quality improvement. PLOS One. 2025;20(6):e0326034. doi:10.1371/journal.pone.0326034
BibTeX
@article{Chen2025,
author = {Chen, Mingming and Tang, Yifan and Qi, Qi and Dai, Hongyi and Lin, Yi and Ling, Chengxiu and Li, Tenglong},
title = {Enhancing stock timing predictions based on multimodal architecture: Leveraging large language models (LLMs) for text quality improvement},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0326034},
doi = {10.1371/journal.pone.0326034}
}
EUVIMED