Design and Verification of a Deep Learning-Driven Risk Warning System for High-Frequency Quantitative Trading

DOI

10.2991/978-94-6463-916-2_48How to use a DOI?

Keywords

High-Frequency Trading; Quantitative Trading; Risk Warning; Deep Learning; LSTM; Financial Risk Management

Abstract

The rise of high-frequency trading (HFT) has drastically transformed financial market microstructure and brought about unheard-of speed and complexity. While HFT enhances liquidity and facilitates price discovery, it also introduces significant systemic risks, such as flash crashes and liquidity vacuums, which can occur within milliseconds. Risk management systems designed for slower trading environments are insufficient to monitor and address these rapidly emerging risks. This paper proposes the design and validation of a novel HFT risk warning system through the application of deep learning. We use a Long Short-Term Memory (LSTM) network, which is a type of Recurrent Neural Network (RNN), to analyze high-dimensional data from limit order books in a time series format. When the model is trained on historical tick-level data, it learns to predict the upcoming probability of a sharp price drop or liquidity crisis. We conduct a rigorous validation: comparing the LSTM model’s performance against simpler machine learning models such as Logistic Regression and Support Vector Machines.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sifan Lin
PY  - 2025
DA  - 2025/12/22
TI  - Design and Verification of a Deep Learning-Driven Risk Warning System for High-Frequency Quantitative Trading
BT  - Proceedings of the 2025 4th International Conference on Public Service, Economic Management and Sustainable Development (PESD 2025)
PB  - Atlantis Press
SP  - 447
EP  - 453
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-916-2_48
DO  - 10.2991/978-94-6463-916-2_48
ID  - Lin2025
ER  -