We are glad to share with you that our recent international conference paper “FinBERT-Driven Sentiment Analysis and Multi-Factor Synergy for Stock Market Forecasting” from our MSAAI student Xiaowen Sha, which has been accepted in 2026 International Conference on Generative Artificial Intelligence for Business (2026 GAIB):
- Xiaowen Sha, Harris Sik-Ho Tsang, Richard Tai-Chiu Hsung, Wai-Lun Lo, Tony Yulin Zhu, Xiaoxing Yang, Zhicong Song, Yui-Lam Chan, “FinBERT-Driven Sentiment Analysis and Multi-Factor Synergy for Stock Market Forecasting,” International Conference on Generative Artificial Intelligence for Business (GAIB), Shenzhen, China, Jul.-Aug. 2026.
Paper Abstract
In the modern financial ecosystem, the inherent volatility and nonlinearity of stock markets necessitate predictive frameworks that transcend traditional quantitative indicators. Conventional forecasting methods often struggle to reconcile the noise of retail investor sentiment with the signal of corporate fundamentals, leading to suboptimal decision-making in automated trading and risk management.
In this paper, we propose a multi-modal fusion framework for stock price forecasting that harmonizes unstructured textual data, structured financial factors, and historical transaction sequences. At the core of our approach, FinBERT, a domain-specific transformer-based model, is proposed to quantify investor sentiment from Chinese stock forum while financial factor engineering is optimized through Information Coefficient (IC) analysis. To address the complexity
of market behavior, we introduce a hybrid architecture where a Transformer encoder captures long-range temporal dependencies across the fused feature space, while a Support Vector Regression (SVR) head ensures robust generalization. Experiments are evaluated on CSI 300 index stocks spanning 2014 to 2024. Our framework achieved an average R-squared exceeding 0.9 and an average RMSE of 0.0401, significantly outperforming individual baseline models and demonstrating robust generalization across diverse market sectors.
The research team members
Hong Kong Chu Hai College
- Ms Xiaowen Sha, Master Student in the Department of Computer Science
- Dr Harris Sik-Ho Tsang, Assistant Professor in the Department of Computer Science
- Dr Richard Tai-Chiu Hsung, Associate Professor in the Department of Computer Science
- Prof. Wai Lun Lo, Professor and Head of the Department of Computer Science
- Dr Tony Yulin Zhu, Assistant Professor in the Department of Computer Science
- Dr Xiaoxing Yang, Assistant Professor in the Department of Computer Science
Guangzhou Vocational University of Science and Technology
- Mr. Zhicong Song, Lecturer in School of Artificial Intelligence and Big Data
The Hong Kong Polytechnic University
- Prof. Yui-Lam Chan, Associate Professor and Associate Head in the Department of Electrical and Electronic Engineering
Some photos of the authors and papers
Our Proposed System Architecture Schema of the Proposed FinBERT-Transformer-SVR Pipeline.
Actual vs Predicted Price Paths for Kweichow Moutai and PetroChina.
