Cited By
View all- ELOMARI-KESSAB SMaitrier GBonart JBouchaud J(2024)Microstructure Modes -- Disentangling the Joint Dynamics of Prices & Order FlowSSRN Electronic Journal10.2139/ssrn.4831906Online publication date: 2024
Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness
Pages 27 - 35
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.
References
[1]
Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein generative adversarial networks. In Proc. of ICML.
[2]
Yuanlu Bai, Henry Lam, Tucker Balch, and Svitlana Vyetrenko. 2022. Efficient Calibration of Multi-Agent Simulation Models from Output Series with Bayesian Optimization. In Proc. of ICAIF.
[3]
Tucker Hybinette Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette, and David Byrd. 2019. How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?arXiv:1906.12010 (2019).
[4]
Battista Biggio, Igino Corona, Davide Maiorca, Blaine Nelson, Nedim Šrndić, Pavel Laskov, Giorgio Giacinto, and Fabio Roli. 2013. Evasion attacks against machine learning at test time. In Proc. of ECML PKDD.
[5]
Ali Borji. 2019. Pros and cons of GAN evaluation measures. Computer Vision and Image Understanding 179 (2019), 41–65.
[6]
Jean-Philippe Bouchaud, Julius Bonart, Jonathan Donier, and Martin Gould. 2018. Trades, quotes and prices: financial markets under the microscope. Cambridge University Press.
[7]
Hans Bühler, Blanka Horvath, Terry J. Lyons, Imanol Perez Arribas, and Ben Wood. 2020. A Data-driven Market Simulator for Small Data Environments. arXiv:2006.14498 (2020).
[8]
Andrea Coletta, Sriram Gopalakrishan, Daniel Borrajo, and Svitlana Vyetrenko. 2023. On the Constrained Time-Series Generation Problem. arXiv preprint arXiv:2307.01717 (2023).
[9]
Andrea Coletta, Joseph Jerome, Rahul Savani, and Svitlana Vyetrenko. 2023. Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness. arXiv preprint arXiv:2306.12806 (2023).
[10]
Andrea Coletta, Aymeric Moulin, Svitlana Vyetrenko, and Tucker Balch. 2022. Learning to simulate realistic limit order book markets from data as a World Agent. In Proc. of ICAIF.
[11]
Andrea Coletta, Matteo Prata, Michele Conti, Emanuele Mercanti, Novella Bartolini, Aymeric Moulin, Svitlana Vyetrenko, and Tucker Balch. 2021. Towards realistic market simulations: a generative adversarial networks approach. In Proc. of ICAIF.
[12]
Andrea Coletta, Svitlana Vyetrenko, and Tucker Balch. 2023. K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs. In Proc. of ICML.
[13]
Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. 2022. Diffusion models in vision: A survey. arXiv:2209.04747 (2022).
[14]
Vincent Darley and Alexander Outkin. 2007. A NASDAQ Market Simulation: Insights on a Major Market from the Science of Complex Adaptive Systems. World Scientific.
[15]
Cristóbal Esteban, Stephanie L. Hyland, and Gunnar Rätsch. 2017. Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs. CoRR abs/1706.02633 (2017).
[16]
Sascha Frey, Kang Li, Peer Nagy, Silvia Sapora, Chris Lu, Stefan Zohren, Jakob Foerster, and Anisoara Calinescu. 2023. JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading. arXiv preprint arXiv:2308.13289 (2023).
[17]
Bruno Gasperov and Zvonko Kostanjcar. 2021. Market Making With Signals Through Deep Reinforcement Learning. IEEE Access 9 (2021), 61611–61622.
[18]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Proc. of NIPS.
[19]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
[20]
Martin D Gould, Mason A Porter, Stacy Williams, Mark McDonald, Daniel J Fenn, and Sam D Howison. 2013. Limit Order Books. Quantitative Finance 13, 11 (2013), 1709–1742.
[21]
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. 2017. Improved training of Wasserstein GANs. In Proc. of NIPS.
[22]
Nikolaus Hautsch and Ruihong Huang. 2012. The market impact of a limit order. Jour. of Econ. Dyn. and Cont. 36, 4 (2012), 501–522.
[23]
Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Proc. of NeurIPS (2020).
[24]
Ruihong Huang and Tomas Polak. 2011. LOBSTER: Limit order book reconstruction system. Available at SSRN 1977207 (2011).
[25]
Hanna Hultin, Henrik Hult, Alexandre Proutiere, Samuel Samama, and Ala Tarighati. 2023. A generative model of a limit order book using recurrent neural networks. Quantitative Finance (2023), 1–28.
[26]
Joseph Jerome, Gregory Palmer, and Rahul Savani. 2022. Market Making with Scaled Beta Policies. In Proc. of ICAIF.
[27]
Chia-Hsuan Kuo, Chiao-Ting Chen, Sin-Jing Lin, and Szu-Hao Huang. 2021. Improving Generalization in Reinforcement Learning-Based Trading by Using a Generative Adversarial Market Model. IEEE Access 9 (2021), 50738–50754.
[28]
Francesco Lamperti, Andrea Roventini, and Amir Sani. 2018. Agent-based model calibration using machine learning surrogates. Jour. of Econ. Dyn. and Cont. 90 (2018), 366–389.
[29]
Junyi Li, Xintong Wang, Yaoyang Lin, Arunesh Sinha, and Michael P. Wellman. 2020. Generating Realistic Stock Market Order Streams. In Proc. of AAAI.
[30]
Benoit B Mandelbrot and Richard L Hudson. 2010. The (mis) behaviour of markets: a fractal view of risk, ruin and reward. Profile books.
[31]
Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv:1411.1784 (2014).
[32]
Peer Nagy, Sascha Frey, Silvia Sapora, Kang Li, Anisoara Calinescu, Stefan Zohren, and Jakob Foerster. 2023. Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network. arXiv preprint arXiv:2309.00638 (2023).
[33]
Yuriy Nevmyvaka, Yi Feng, and Michael Kearns. 2006. Reinforcement learning for optimized trade execution. In Proc. of ICML.
[34]
Anh Nguyen, Jason Yosinski, and Jeff Clune. 2015. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proc. of CVPR.
[35]
Brian Ning, Franco Ho Ting Lin, and Sebastian Jaimungal. 2021. Double Deep Q-Learning for Optimal Execution. Applied Mathematical Finance 28, 4 (2021), 361–380.
[36]
Robert Pardo. 2008. The Evaluation and Optimization of Trading Strategies, 2nd Ed. Wiley.
[37]
Lerrel Pinto, James Davidson, Rahul Sukthankar, and Abhinav Gupta. 2017. Robust Adversarial Reinforcement Learning. In Proc. of ICML.
[38]
Donovan Platt. 2020. A comparison of economic agent-based model calibration methods. Jour. of Econ. Dyn. and Cont. 113 (2020), 32 pages.
[39]
Donovan Platt and Tim Gebbie. 2017. The Problem of Calibrating an Agent-Based Model of High-Frequency Trading. arXiv:1606.01495 (2017).
[40]
Arnau Quera-Bofarull, Ayush Chopra, Joseph Aylett-Bullock, Carolina Cuesta-Lazaro, Anisoara Calinescu, Ramesh Raskar, and Michael Wooldridge. 2023. Don’t Simulate Twice: One-Shot Sensitivity Analyses via Automatic Differentiation. In Proc. of AAMAS.
[41]
Kashif Rasul, Calvin Seward, Ingmar Schuster, and Roland Vollgraf. 2021. Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting. In Proc. of ICML.
[42]
Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs M. Bergmann, and Roland Vollgraf. 2021. Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows. In Proc. of ICLR.
[43]
Nataniel Ruiz, Samuel Schulter, and Manmohan Chandraker. 2019. Learning To Simulate. In Proc. of ICLR.
[44]
Zijian Shi and John Cartlidge. 2023. Neural Stochastic Agent-Based Limit Order Book Simulation: A Hybrid Methodology. In Proc. of AAMAS.
[45]
Justin A Sirignano. 2019. Deep learning for limit order books. Quantitative Finance 19, 4 (2019), 549–570.
[46]
Thomas Spooner, John Fearnley, Rahul Savani, and Andreas Koukorinis. 2018. Market Making via Reinforcement Learning. In Proc. of AAMAS.
[47]
Thomas Spooner and Rahul Savani. 2020. Robust Market Making via Adversarial Reinforcement Learning. In Proc. of IJCAI.
[48]
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv:1312.6199 (2013).
[49]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proc. of NIPS.
[50]
Svitlana Vyetrenko, David Byrd, Nick Petosa, Mahmoud Mahfouz, Danial Dervovic, Manuela Veloso, and Tucker Balch. 2020. Get real: realism metrics for robust limit order book market simulations. In Proc. of ICAIF.
[51]
Song Wei, Andrea Coletta, Svitlana Vyetrenko, and Tucker Balch. 2023. ATMS: Algorithmic Trading-Guided Market Simulation. arXiv preprint arXiv:2309.01784 (2023).
[52]
Yufei Wu, Mahmoud Mahfouz, Daniele Magazzeni, and Manuela Veloso. 2022. Towards Robust Representation of Limit Orders Books for Deep Learning Models. arXiv:2110.05479 (2022).
[53]
Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, and Kalyan Veeramachaneni. 2019. Modeling Tabular data using Conditional GAN. In Proc. of NeurIPS.
[54]
Zihao Zhang, Stefan Zohren, and Stephen Roberts. 2019. DeepLOB: Deep convolutional neural networks for limit order books. IEEE Transactions on Signal Processing 67, 11 (2019), 3001–3012.
[55]
Ban Zheng, Eric Moulines, and Frédéric Abergel. 2012. Price jump prediction in limit order book. arXiv:1204.1381 (2012).
[56]
Linqi Zhou, Michael Poli, Winnie Xu, Stefano Massaroli, and Stefano Ermon. 2023. Deep latent state space models for time-series generation. In Proc. of ICML.
Index Terms
- Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness
Index terms have been assigned to the content through auto-classification.
Recommendations
Learning to simulate realistic limit order book markets from data as a World Agent
ICAIF '22: Proceedings of the Third ACM International Conference on AI in FinanceMulti-agent market simulators usually require careful calibration to emulate real markets, which includes the number and the type of agents. Poorly calibrated simulators can lead to misleading conclusions, potentially causing severe loss when employed ...
Macroeconomic Determinants of the Behavior of Dhaka Stock Exchange DSE
Many past studies documented a strong evidence of a linkage between stock prices and macroeconomic activities across different stock markets and time horizons. However, most of these studies have focused on developed economies and highlighted the impact ...
Next-generation securities market systems: an experimental investigation of quote-driven and order-driven trading
Special section: Strategic and competitive information systemsSeveral major securities markets including Nasdaq in the United States and the London Stock Exchange's SEAQ are organized as dealer markets that use computer screen displays of competitive dealer quotes to establish fair trade prices. To improve their ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
November 2023
697 pages
ISBN:9798400702402
DOI:10.1145/3604237
Copyright © 2023 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 25 November 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICAIF '23
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 565Total Downloads
- Downloads (Last 12 months)548
- Downloads (Last 6 weeks)64
Reflects downloads up to 13 Dec 2024
Other Metrics
Citations
Cited By
View all- ELOMARI-KESSAB SMaitrier GBonart JBouchaud J(2024)Microstructure Modes -- Disentangling the Joint Dynamics of Prices & Order FlowSSRN Electronic Journal10.2139/ssrn.4831906Online publication date: 2024
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in