FINTECH THRUST SEMINAR | Deep Learning in High-Frequency Trading: Opportunities, Challenges, and Real-World Applications
Deep Learning in High-Frequency Trading: Opportunities, Challenges, and Real-World Applications
Abstract:
High-frequency trading (HFT) and quantitative finance generate massive streams of market data, making them prime candidates for deep learning methods. In this talk, we will explore how neural networks can capture short-term price movements, model limit order book dynamics, and enhance risk management. We will discuss the challenges unique to HFT - such as ultra-low latency, fleeting alpha signals, and high-dimensional data - and show how recent advances in deep learning address these issues. Real-world case studies will illustrate the practical impact of these techniques, guiding us toward the skills and insights needed to thrive in algorithmic trading and quantitative research.
Dr. Zhang is currently a quantitative researcher at Micro Trading, specializing in predictive modeling and execution strategies. He was previously a postdoctoral researcher at the Oxford-Man Institute, University of Oxford. Dr. Zhang obtained his Ph.D. in Engineering Science from the University of Oxford, where he focused on deep learning and deep reinforcement learning.