Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness

Coletta, Andrea ORCID: 0000-0003-1401-1715, Jerome, Joseph ORCID: 0000-0002-8312-0053, Savani, Rahul ORCID: 0000-0003-1262-7831 and Vyetrenko, Svitlana ORCID: 0000-0001-7650-9880 (2023) Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness. In: ICAIF '23: 4th ACM International Conference on AI in Finance.

Access the full-text of this item by clicking on the Open Access link.

Official URL: http://dx.doi.org/10.1145/3604237.3626854

Abstract

Limit order books are a fundamental and widespread market mechanism. This paper investigates the use of conditional generative models for order book simulation. For developing a trading agent, this approach has drawn recent attention as an alternative to traditional backtesting, due to its ability to react to the presence of the trading agent. We explore the dependence of a state-of-the-art conditional generative adversarial network (CGAN) upon its input features, highlighting both strengths and weaknesses. To do this, we use "adversarial attacks"on the model's features and its mechanism. We then show how these insights can be used to improve the CGAN, both in terms of its realism and robustness. We finish by laying out a roadmap for future work.

Item Type:	Conference or Workshop Item (Unspecified)
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	27 Nov 2023 09:07
Last Modified:	29 Dec 2023 14:48
DOI:	10.1145/3604237.3626854
Open Access URL:	https://dl.acm.org/doi/10.1145/3604237.3626854
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3177014