Flexible Target Prediction for Quantitative Trading in the American Stock Market: A Hybrid Framework Integrating Ensemble Models, Fusion Models and Transfer Learning
Entropy · 11.01.2026 · 28 (1) · 84
DOI: 10.3390/e28010084 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 11.01.2026. Verfasst von Keyue Yan und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Data Science and Artificial Intelligence, Guangdong University of Finance, Guangzhou 510521, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong University of Finance Research Start-Up Fund, 2024 Guangdong Province University Youth Innovation Talent Project.
Abstract (Originalsprache)
Stock price prediction is a core challenge in quantitative finance. While machine learning has advanced the modeling of complex financial time series, existing methods often rely on single-target predictions, underutilize multidimensional market information, and are disconnected from practical trading systems. To address these gaps, this research develops a hybrid machine learning framework for flexible target forecasting and systematic trading of major American technology stocks. The framework integrates Ensemble Models (AdaBoost, Decision Tree, LightGBM, Random Forest, XGBoost) with Fusion Models (Voting, Stacking, Blending) and introduces a Transfer Learning method enhanced by Dynamic Time Warping to facilitate knowledge sharing across assets, improving robustness. Focusing on ten key stocks, we forecast three distinct momentum indicators: next-day Closing Price Difference, Moving Average Difference, and Exponential Moving Average Difference. Empirical results demonstrate that the proposed Transfer Learning approach achieves superior predictive performance and trading simulations confirm that strategies based on these predicted momentum signals generate substantial returns. This research demonstrates that the proposed hybrid machine learning framework can mitigate the high information entropy inherent in financial markets, offering a systematic and practical method for integrating machine learning with quantitative trading.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Data Science and Artificial Intelligence, Guangdong University of Finance, Guangzhou 510521, China.
- Choi Kai Yau College, University of Macau, Macau SAR 999078, China.
- School of International and Continuing Education, Beijing Institute of Technology (Zhuhai), Zhuhai 519088, China.
- School of Computer Science and Artificial Intelligence, Foshan University, Foshan 528225, China.
- School of Computer Engineering, Guangzhou City University of Technology, Guangzhou 510800, China.
- Beijing Key Laboratory of Commercial Data Security Protection and Intelligent Governance, Beijing Technology and Business University, Beijing 100048, China.
ORCID-Profile: Keyue Yan, Zihuan Yue, Chi Chong Wu, Qiqiao He, Jiaming Zhou, Zhihao Hao, Ying Li
Förderung
- Guangdong University of Finance Research Start-Up Fund
- 2024 Guangdong Province University Youth Innovation Talent Project
Zitieren
APA
Yan, K., Yue, Z., Wu, C. C., He, Q., Zhou, J., Hao, Z., & Li, Y. (2026). Flexible Target Prediction for Quantitative Trading in the American Stock Market: A Hybrid Framework Integrating Ensemble Models, Fusion Models and Transfer Learning. Entropy, 28(1), 84. https://doi.org/10.3390/e28010084
Vancouver
Yan K, Yue Z, Wu CC, He Q, Zhou J, Hao Z, et al. Flexible Target Prediction for Quantitative Trading in the American Stock Market: A Hybrid Framework Integrating Ensemble Models, Fusion Models and Transfer Learning. Entropy. 2026;28(1):84. doi:10.3390/e28010084
BibTeX
@article{Yan2026,
author = {Yan, Keyue and Yue, Zihuan and Wu, Chi Chong and He, Qiqiao and Zhou, Jiaming and Hao, Zhihao and Li, Ying},
title = {Flexible Target Prediction for Quantitative Trading in the American Stock Market: A Hybrid Framework Integrating Ensemble Models, Fusion Models and Transfer Learning},
journal = {Entropy},
year = {2026},
volume = {28},
number = {1},
pages = {84},
doi = {10.3390/e28010084}
}
EUVIMED