Predicting Dynamic Market Liquidity via Temporal Graph Neural Networks Integrating Limit Order Book Evolution and Cross Asset Spillover Effects
Abstract
The modern financial ecosystem is characterized by an intricate web of interdependencies where liquidity is no longer a localized phenomenon but a dynamic state influenced by high-frequency order book evolution and cross-asset spillover effects. Traditional econometric models often fail to capture the non-linear, spatial-temporal relationships inherent in these multi-layered systems. This paper proposes a comprehensive framework for predicting dynamic market liquidity through the deployment of Temporal Graph Neural Networks. By conceptualizing the financial market as a dynamic graph—where nodes represent individual assets and edges represent the strength of information and liquidity transmission—we integrate the granular microstructural data of the Limit Order Book with broader systemic spillover indicators. Our analysis focuses on the system-level architectural trade-offs required to balance predictive accuracy with computational latency in a high-frequency environment. We further explore the socio-technical implications of such systems, including infrastructure robustness, algorithmic governance, and the ethical considerations of liquidity provision in automated markets. Through deep explanatory analysis of deployment challenges and sustainability, the research highlights how temporal graph architectures mitigate the risks of systemic contagion while enhancing market efficiency. The study concludes that the future of liquidity management lies in the transition from asset-specific modeling to global, graph-based infrastructures that account for the reflexivity and interconnectedness of modern global finance.
References
1.Anderson, B., & Chen, J. (2025). The impact of deep learning on market efficiency and price discovery. Journal of Financial Technology, 12(2), 45-67.
2.Biais, B., Glosten, L., & Spatt, C. (2005). Market microstructure: A survey of microfoundations, empirical results, and policy implications. Journal of Financial Markets, 8(2), 217-264.
3.Boucher, J. P., & Maillet, B. (2024). Visual representation learning for multi-asset risk management. Quantitative Finance, 24(8), 1102-1118.
4.Cartea, A., Jaimungal, S., & Penalva, J. (2015). Algorithmic and High-Frequency Trading. Cambridge University Press.
5.Cont, R., Kukanov, A., & Stoikov, S. (2014). The price impact of order book events. Journal of Financial Econometrics, 12(1), 47-88.
6.Davis, R., & Smith, L. (2026). Socio-technical dynamics of automated market makers. IEEE Transactions on Systems, Man, and Cybernetics, 56(1), 12-29.
7.Easley, D., López de Prado, M. M., & O'Hara, M. (2012). The volume clock: Insights into the high-frequency predictability of stock returns. Journal of Portfolio Management, 39(1), 19-29.
8.Fabre, T., & Challet, D. (2025). Learning the spoofability of limit order books with interpretable probabilistic neural networks. Decision Support Systems, 178, 114120.
9.Gatheral, J., & Oomen, R. C. (2010). Zero-intelligence realized variance estimation. Finance and Stochastics, 14(2), 249-283.
10.Hu, L., & Shen, Y. (2026). A predictive analytics approach for forecasting global stock index returns using deep learning techniques. Decision Analytics Journal, 100685.
11.Hasbrouck, J. (2007). Empirical Market Microstructure. Oxford University Press.
12.Huang, B., & Wang, Q. (2026). Deep temporal networks for high-frequency signal processing. Systems Research and Behavioral Science, 43(3), 332-348.
13.Kearns, M., & Nevmyvaka, Y. (2013). Machine learning for market microstructure and high frequency trading. High Frequency Trading: New Realities for Traders, Markets and Regulators.
14.Kolm, P. N., Turiel, J., & Westray, N. (2023). Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book. Mathematical Finance, 33(4), 1044-1081.
15.Kyle, A. P. (1985). Continuous auctions and insider trading. Econometrica, 53(6), 1315-1335.
16.Lehalle, C. A., & Laruelle, S. (2018). Market Microstructure in Practice. World Scientific.
17.Li, X., & Wang, Y. (2026). Sustainability and energy efficiency in high-frequency trading infrastructure. Sustainable Systems Review, 9(3), 204-221.
18.Lopez de Prado, M. M. (2018). Advances in Financial Machine Learning. Wiley.
19.Madhavan, A. (2000). Market microstructure: A survey. Journal of Financial Markets, 3(3), 205-258.
20.Menkveld, A. J. (2013). High frequency trading and the new market makers. Journal of Financial Markets, 16(4), 712-740.
21.O'Hara, M. (2015). High frequency market microstructure. Journal of Financial Economics, 116(2), 257-270.
22.Parlour, C. A., & Seppi, D. J. (2008). Limit order markets: A survey. Handbook of Financial Intermediation and Banking.
23.Rosu, I. (2009). A dynamic model of the limit order book. Review of Financial Studies, 22(11), 4601-4641.
24.Sirignano, J., & Cont, R. (2019). Universal features of price formation in financial markets: Perspectives from deep learning. Quantitative Finance, 19(9), 1449-1459.
25.Stoikov, S. (2018). The micro-price: A high-frequency estimator of future prices. Quantitative Finance, 18(6), 873-881.
26.Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction. MIT Press.
27.Taleb, N. N. (2007). The Black Swan: The Impact of the Highly Improbable. Random House.
28.Tobin, J. (1969). A general equilibrium approach to monetary theory. Journal of Money, Credit and Banking, 1(1), 15-29.
29.Zhang, X., & Chen, Y. (2026). Sustainable AI: Managing the carbon footprint of deep learning infrastructures. Global Environmental Change, 82, 102654.
30.Zhang, Z., Zohren, S., & Roberts, S. (2019). DeepLOB: Deep convolutional neural networks for limit order books. IEEE Transactions on Signal Processing, 67(11), 3001-3012.
31.Zuiderveen Borgesius, F. J. (2018). Discrimination, artificial intelligence, and algorithmic decision-making. Council of Europe.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
