Table of Links Abstract and 1. Introduction Abstract and 1. Introduction 2. Relevant Work 2. Relevant Work 3. Methods 3. Methods 3.1 Models 3.1 Models 3.2 Summarising Features 3.2 Summarising Features 3.3 Calibration of Market Model Parameters 3.3 Calibration of Market Model Parameters 4. Experiments 4. Experiments 4.1 Zero Intelligence Trader 4.1 Zero Intelligence Trader 4.2 Extended Chiarella 4.2 Extended Chiarella 4.3 Historical Data 4.3 Historical Data 5. Discussion & Future Work 5. Discussion & Future Work 6. Significance, Acknowledgments, and References 6. Significance, Acknowledgments, and References 6 SIGNIFICANCE In this work, we demonstrate that neural density estimators can robustly infer the parameters for a market simulator, based on two distinct theoretical models, a zero intelligence trader, and the extended Chiarella model. We combine neural density estimators to calibrate these models without using stylised facts at calibration time, a significant departure from previous methods for calibration of market simulators. Instead, we use the market simulation data directly, such as the mid-price and total volume, providing an unbiased approach to calibration that can efficiently scale. We identify interesting features of both models from our calibration procedure due to the explicit posterior probability distribution that is calculated around each parameter value, and identify future extensions and frameworks where our work can be used. ACKNOWLEDGMENTS We would like to thank the NVIDIA LaunchPad Experience for their help with providing compute resources for this research, especially David Taubenheim, Rafah El-Khatib, Alvin Clark and Jochen Papenbrock. REFERENCES [1] Selim Amrouni, Aymeric Moulin, Jared Vann, Svitlana Vyetrenko, Tucker Balch, and Manuela Veloso. 2021. ABIDES-gym: gym environments for multi-agent discrete event simulation and application to financial markets. In Proceedings of the Second ACM International Conference on AI in Finance. 1–9. [2] Robert L Axtell and J Doyne Farmer. 2022. Agent-based modeling in economics and finance: past, present, and future. Journal of Economic Literature (2022). [3] Yuanlu Bai, Henry Lam, Tucker Balch, and Svitlana Vyetrenko. 2022. Efficient Calibration of Multi-Agent Simulation Models from Output Series with Bayesian Optimization. In Proceedings of the Third ACM International Conference on AI in Finance. 437–445. [4] Jean-Philippe Bouchaud and Marc Potters. 2001. More stylized facts of financial markets: leverage effect and downside correlations. Physica A: Statistical Mechanics and its Applications 299, 1-2 (2001), 60–70. [5] Johann Brehmer. 2021. Simulation-based inference in particle physics. Nature Reviews Physics 3, 5 (2021), 305–305. [6] Hans Buehler, Blanka Horvath, Terry Lyons, Imanol Perez Arribas, and Ben Wood. 2020. A data-driven market simulator for small data environments. arXiv preprint arXiv:2006.14498 (2020). [7] David Byrd, Maria Hybinette, and Tucker Hybinette Balch. 2019. Abides: Towards high-fidelity market simulation for ai research. arXiv preprint arXiv:1904.12066 (2019). [8] Patrick Cannon, Daniel Ward, and Sebastian M. Schmon. 2022. Investigating the Impact of Model Misspecification in Neural Simulation-based Inference. arXiv:2209.01845 [stat.ML] [9] Qinkai Chen and Christian-Yann Robert. 2022. Multivariate Realized Volatility Forecasting with Graph Neural Network. In Proceedings of the Third ACM International Conference on AI in Finance. 156–164. [10] Carl Chiarella. 1992. The dynamics of speculative behaviour. Annals of operations research 37, 1 (1992), 101–123. [11] Samuel N Cohen, Derek Snow, and Lukasz Szpruch. 2021. Black-box model risk in finance. arXiv preprint arXiv:2102.04757 (2021). [12] 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 Proceedings of the Second ACM International Conference on AI in Finance. 1–9. [13] Rama Cont. 2001. Empirical properties of asset returns: stylized facts and statistical issues. Quantitative finance 1, 2 (2001), 223. [14] Kyle Cranmer, Johann Brehmer, and Gilles Louppe. 2020. The frontier of simulation-based inference. Proceedings of the National Academy of Sciences 117, 48 (2020), 30055–30062. [15] Nicols Cruz and Javier Ruiz-del Solar. 2020. Closing the simulation-to-reality gap using generative neural networks: Training object detectors for soccer robotics in simulation as a case study. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 1–8. [16] Conor Durkan, Artur Bekasov, Iain Murray, and George Papamakarios. 2019. Neural spline flows. Advances in neural information processing systems 32 (2019). [17] Joel Dyer, Patrick Cannon, J Doyne Farmer, and Sebastian Schmon. 2022. Blackbox Bayesian inference for economic agent-based models. arXiv preprint arXiv:2202.00625 (2022). [18] Joel Dyer, Patrick Cannon, J Doyne Farmer, and Sebastian M Schmon. 2022. Calibrating agent-based models to microdata with graph neural networks. arXiv preprint arXiv:2206.07570 (2022). [19] David Easley, Marcos M Lopez De Prado, and Maureen O’Hara. 2011. The microstructure of the “flash crash”: flow toxicity, liquidity crashes, and the probability of informed trading. The Journal of Portfolio Management 37, 2 (2011), 118–128. [20] Giorgio Fagiolo, Mattia Guerini, Francesco Lamperti, Alessio Moneta, and Andrea Roventini. 2019. Validation of agent-based models in economics and finance. Computer simulation validation: fundamental concepts, methodological frameworks, and philosophical perspectives (2019), 763–787. [21] Kang Gao, Perukrishnen Vytelingum, Stephen Weston, Wayne Luk, and Ce Guo. 2022. Understanding intra-day price formation process by agent-based financial market simulation: calibrating the extended chiarella model. arXiv preprint arXiv:2208.14207 (2022). [22] Pedro J Gonçalves, Jan-Matthis Lueckmann, Michael Deistler, Marcel Nonnenmacher, Kaan Öcal, Giacomo Bassetto, Chaitanya Chintaluri, William F Podlaski, Sara A Haddad, Tim P Vogels, et al. 2020. Training deep neural density estimators to identify mechanistic models of neural dynamics. Elife 9 (2020), e56261. [23] 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. [24] David Greenberg, Marcel Nonnenmacher, and Jakob Macke. 2019. Automatic posterior transformation for likelihood-free inference. In International Conference on Machine Learning. PMLR, 2404–2414. [25] Filip Guzy, Michał Woźniak, and Bartosz Krawczyk. 2021. Evaluating and explaining generative adversarial networks for continual learning under concept drift. In 2021 International Conference on Data Mining Workshops (ICDMW). IEEE, 295–303. [26] Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. Ganspace: Discovering interpretable gan controls. Advances in Neural Information Processing Systems 33 (2020), 9841–9850. [27] Joeri Hermans, Volodimir Begy, and Gilles Louppe. 2020. Likelihood-free mcmc with amortized approximate ratio estimators. In International conference on machine learning. PMLR, 4239–4248. [28] Daolang Huang, Ayush Bharti, Amauri Souza, Luigi Acerbi, and Samuel Kaski. 2023. Learning Robust Statistics for Simulation-based Inference under Model Misspecification. arXiv:2305.15871 [stat.ML] [29] Ivan Kobyzev, Simon JD Prince, and Marcus A Brubaker. 2020. Normalizing flows: An introduction and review of current methods. IEEE transactions on pattern analysis and machine intelligence 43, 11 (2020), 3964–3979. [30] Adam A Majewski, Stefano Ciliberti, and Jean-Philippe Bouchaud. 2020. Coexistence of trend and value in financial markets: Estimating an extended Chiarella model. Journal of Economic Dynamics and Control 112 (2020), 103791. [31] George Papamakarios. 2019. Neural density estimation and likelihood-free inference. arXiv preprint arXiv:1910.13233 (2019). [32] George Papamakarios and Iain Murray. 2016. Fast 𝜀-free inference of simulation models with bayesian conditional density estimation. Advances in neural information processing systems 29 (2016). [33] George Papamakarios, Theo Pavlakou, and Iain Murray. 2017. Masked autoregressive flow for density estimation. Advances in neural information processing systems 30 (2017). [34] Vasiliki Plerou, Parameswaran Gopikrishnan, Bernd Rosenow, Luis AN Amaral, and H Eugene Stanley. 2000. Econophysics: financial time series from a statistical physics point of view. Physica A: Statistical Mechanics and its Applications 279, 1-4 (2000), 443–456. [35] Tobias Preis, Sebastian Golke, Wolfgang Paul, and Johannes J Schneider. 2006. Multi-agent-based order book model of financial markets. Europhysics Letters 75, 3 (2006), 510. [36] Egle Samanidou, Elmar Zschischang, Dietrich Stauffer, and Thomas Lux. 2007. Agent-based models of financial markets. Reports on Progress in Physics 70, 3 (2007), 409. [37] Zijian Shi and John Cartlidge. 2023. Neural Stochastic Agent-Based Limit Order Book Simulation: A Hybrid Methodology. arXiv preprint arXiv:2303.00080 (2023). [38] George J Stigler. 1963. Public regulation of the securities markets. Bus. Law. 19 (1963), 721. [39] Namid R Stillman, Silke Henkes, Roberto Mayor, and Gilles Louppe. 2023. Graphinformed simulation-based inference for models of active matter. arXiv preprint arXiv:2304.06806 (2023). [40] Victor Storchan, Svitlana Vyetrenko, and Tucker Balch. 2021. Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators. arXiv preprint arXiv:2108.00664 (2021). [41] Timo Teräsvirta and Zhenfang Zhao. 2011. Stylized facts of return series, robust estimates and three popular models of volatility. Applied financial economics 21, 1-2 (2011), 67–94. [42] 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 Proceedings of the First ACM International Conference on AI in Finance. 1–8. [43] 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. [44] Wenshuai Zhao, Jorge Pena Queralta, Li Qingqing, and Tomi Westerlund. 2020. Towards closing the sim-to-real gap in collaborative multi-robot deep reinforcement learning. In 2020 5th International Conference on Robotics and Automation Engineering (ICRAE). IEEE, 7–12. Authors: (1) Namid R. Stillman, Simudyne Limited, United Kingdom (namid@simudyne.com); (2) Rory Baggott, Simudyne Limited, United Kingdom (rory@simudyne.com); (3) Justin Lyon, Simudyne Limited, United Kingdom (justin@simudyne.com); (4) Jianfei Zhang, Hong Kong Exchanges and Clearing Limited, Hong Kong (jianfeizhang@hkex.com.hk); (5) Dingqiu Zhu, Hong Kong Exchanges and Clearing Limited, Hong Kong (dingqiuzhu@hkex.com.hk); (6) Tao Chen, Hong Kong Exchanges and Clearing Limited, Hong Kong (taochen@hkex.com.hk); (7) Perukrishnen Vytelingum, Simudyne Limited, United Kingdom (krishnen@simudyne.com). Authors: Authors: (1) Namid R. Stillman, Simudyne Limited, United Kingdom (namid@simudyne.com); (2) Rory Baggott, Simudyne Limited, United Kingdom (rory@simudyne.com); (3) Justin Lyon, Simudyne Limited, United Kingdom (justin@simudyne.com); (4) Jianfei Zhang, Hong Kong Exchanges and Clearing Limited, Hong Kong (jianfeizhang@hkex.com.hk); (5) Dingqiu Zhu, Hong Kong Exchanges and Clearing Limited, Hong Kong (dingqiuzhu@hkex.com.hk); (6) Tao Chen, Hong Kong Exchanges and Clearing Limited, Hong Kong (taochen@hkex.com.hk); (7) Perukrishnen Vytelingum, Simudyne Limited, United Kingdom (krishnen@simudyne.com). This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv
