From Market Volatility to Predictive Insight: An Adaptive Transformer–RL Framework for Sentiment-Driven Financial Time-Series Forecasting

Zhicong Song, Harris Sik-Ho Tsang (), Richard Tai-Chiu Hsung, Yulin Zhu and Wai-Lun Lo
Additional contact information
Zhicong Song: Department of Computer Science, Hong Kong Chu Hai College, Hong Kong 999077, China
Harris Sik-Ho Tsang: Department of Computer Science, Hong Kong Chu Hai College, Hong Kong 999077, China
Richard Tai-Chiu Hsung: Department of Computer Science, Hong Kong Chu Hai College, Hong Kong 999077, China
Yulin Zhu: Department of Computer Science, Hong Kong Chu Hai College, Hong Kong 999077, China
Wai-Lun Lo: Department of Computer Science, Hong Kong Chu Hai College, Hong Kong 999077, China

Forecasting, 2025, vol. 7, issue 4, 1-29

Abstract: 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.

Keywords: sentiment analysis; Transformer; reinforcement learning; market price prediction; model ensembling (search for similar items in EconPapers)
JEL-codes: A1 B4 C0 C1 C2 C3 C4 C5 C8 M0 Q2 Q3 Q4 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2571-9394/7/4/55/pdf (application/pdf)
https://www.mdpi.com/2571-9394/7/4/55/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jforec:v:7:y:2025:i:4:p:55-:d:1763898

Access Statistics for this article

Forecasting is currently edited by Ms. Joss Chen

More articles in Forecasting from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().