Publication Date

2025

Document Type

Dissertation/Thesis

First Advisor

Hua, Lei L.

Degree Name

Ph.D. (Doctor of Philosophy)

Legacy Department

Department of Mathematical Sciences

Abstract

High-frequency trading (HFT) has emerged as a pivotal innovation in modern financial markets, characterized by rapid, data-driven decision-making processes that capitalize on granular, time-stamped market data. This dissertation examines the predictability of intraday stock price movements during the final 30 minutes of U.S. trading, employing a Bayesian regression model with Student-t error terms to address the limitations of traditional Gaussian-based methods. The analysis reveals a decline in established predictors and the emergence of new dynamics, such as post-Federal Reserve "tug-of-war" effects. The research further advances high-frequency financial modeling by introducing a comprehensive data engineering pipeline and applying cutting-edge deep learning models, including DeepAR, Mamba, and Transformers. Enhanced with Student-t noise, DeepAR demonstrates superior predictive performance. A game-theory-based interpretability framework highlights the critical role of order flow imbalances, offering actionable insights for feature selection. These findings emphasize the transformative potential of advanced modeling techniques and robust data engineering in high-frequency financial research and practice.

Extent

97 pages

Language

en

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Download

Share

COinS