From Market Volatility to Predictive Insight: An Adaptive Transformer–RL Framework for Sentiment-Driven Financial Time-Series Forecasting
Forecasting · 02.10.2025 · 7 (4) · 55
DOI: 10.3390/forecast7040055 ↗Kurz gefasst
Fachartikel in der Zeitschrift Forecasting, online erschienen am 02.10.2025. Verfasst von Zhicong Song und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hong Kong Chu Hai College.
Abstract (Originalsprache)
Financial time-series prediction remains a significant challenge, driven by market volatility, nonlinear dynamic characteristics, and the complex interplay between quantitative indicators and investor sentiment. Traditional time-series models (e.g., ARIMA and GARCH) struggle to capture the nuanced sentiment in textual data, while static deep learning integration methods fail to adapt to market regime transitions (bull markets, bear markets, and consolidation). This study proposes a hybrid framework that integrates investor forum sentiment analysis with adaptive deep reinforcement learning (DRL) for dynamic model integration. By constructing a domain-specific financial sentiment dictionary (containing 16,673 entries) based on the sentiment analysis approach and word-embedding technique, we achieved up to 97.35% accuracy in forum title classification tasks. Historical price data and investor forum sentiment information were then fed into a Support Vector Regressor (SVR) and three Transformer variants (single-layer, multi-layer, and bidirectional variants) for predictions, with a Deep Q-Network (DQN) agent dynamically fusing the prediction results. Comprehensive experiments were conducted on diverse financial datasets, including China Unicom, the CSI 100 index, corn, and Amazon (AMZN). The experimental results demonstrate that our proposed approach, combining textual sentiment with adaptive DRL integration, significantly enhances prediction robustness in volatile markets, achieving the lowest RMSEs across diverse assets. It overcomes the limitations of static methods and multi-market generalization, outperforming both benchmark and state-of-the-art models.
Förderung
- Hong Kong Chu Hai College
Zitieren
APA
Song, Z., Tsang, H. S., Hsung, R. T., Zhu, Y., & Lo, W. (2025). From Market Volatility to Predictive Insight: An Adaptive Transformer–RL Framework for Sentiment-Driven Financial Time-Series Forecasting. Forecasting, 7(4), 55. https://doi.org/10.3390/forecast7040055
Vancouver
Song Z, Tsang HS, Hsung RT, Zhu Y, Lo W. From Market Volatility to Predictive Insight: An Adaptive Transformer–RL Framework for Sentiment-Driven Financial Time-Series Forecasting. Forecasting. 2025;7(4):55. doi:10.3390/forecast7040055
BibTeX
@article{Song2025,
author = {Song, Zhicong and Tsang, Harris Sik-Ho and Hsung, Richard Tai-Chiu and Zhu, Yulin and Lo, Wai-Lun},
title = {From Market Volatility to Predictive Insight: An Adaptive Transformer–RL Framework for Sentiment-Driven Financial Time-Series Forecasting},
journal = {Forecasting},
year = {2025},
volume = {7},
number = {4},
pages = {55},
doi = {10.3390/forecast7040055}
}
EUVIMED