Towards realistic market simulations: a generative adversarial networks approach

Simulated environments are increasingly used by trading firms and investment banks to evaluate trading strategies before approaching real markets. Backtesting, a widely used approach, consists of simulating experimental strategies while replaying historical market scenarios. Unfortunately, this approach does not capture the market response to the experimental agents’ actions. In contrast, multi-agent simulation presents a natural bottom-up approach to emulating agent interaction in financial markets. It allows to set up pools of traders with diverse strategies to mimic the financial market trader population, and test the performance of new experimental strategies. Since individual agent-level historical data is typically proprietary and not available for public use, it is difficult to calibrate multiple market agents to obtain the realism required for testing trading strategies. To addresses this challenge we propose a synthetic market generator based on Conditional Generative Adversarial Networks (CGANs) trained on real aggregate-level historical data. A CGAN-based "world" agent can generate meaningful orders in response to an experimental agent. We integrate our synthetic market generator into ABIDES, an open source simulator of financial markets. By means of extensive simulations we show that our proposal outperforms previous work in terms of stylized facts reflecting market responsiveness and realism. ACM Reference Format: 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 ACM Conference (ICAIF’21). ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/nnnnnnn.nnnnnnn

[1]  John Fearnley,et al.  Market Making via Reinforcement Learning , 2018, AAMAS.

[2]  Isao Yagi,et al.  Analysis of the impact of maker-taker fees on the stock market using agent-based simulation , 2020, ICAIF.

[3]  J. Farmer,et al.  The Predictive Power of Zero Intelligence in Financial Markets , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[4]  P. Alam.  ‘A’ , 2021, Composites Engineering: An A–Z Guide.

[5]  Dmitry Efimov,et al.  Using generative adversarial networks to synthesize artificial financial datasets , 2020, ArXiv.

[6]  Kumiko Tanaka-Ishii,et al.  Modeling financial time-series with generative adversarial networks , 2019, Physica A: Statistical Mechanics and its Applications.

[7]  David Byrd.  Explaining Agent-Based Financial Market Simulation , 2019, ArXiv.

[8]  Michael P. Wellman,et al.  Generating Realistic Stock Market Order Streams , 2020, AAAI.

[9]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[10]  J. Teichmann,et al.  Deep hedging , 2018, Quantitative Finance.

[11]  Sameena Shah,et al.  Simulating and classifying behavior in adversarial environments based on action-state traces: an application to money laundering , 2020, ICAIF.

[12]  Michael P. Wellman,et al.  Market Manipulation: An Adversarial Learning Framework for Detection and Evasion , 2020, IJCAI.

[13]  Maria Hybinette,et al.  How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation? , 2019, ArXiv.

[14]  Wing Lon Ng,et al.  Can a zero-intelligence plus model explain the stylized facts of financial time series data? , 2012, AAMAS.

[15]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[16]  Gershon Wolansky,et al.  Optimal Transport , 2021 .

[17]  Manuela Veloso,et al.  Get real: realism metrics for robust limit order book market simulations , 2019, ICAIF.

[18]  David Byrd,et al.  ABIDES: Towards High-Fidelity Multi-Agent Market Simulation , 2020, SIGSIM-PADS.

[19]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[20]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[21]  Samuel A. Assefa.  Generating synthetic data in finance: opportunities, challenges and pitfalls , 2020, ICAIF.

[22]  Mihaela van der Schaar,et al.  Time-series Generative Adversarial Networks , 2019, NeurIPS.

[23]  F. Abergel,et al.  Econophysics review: I. Empirical facts , 2011 .

[24]  Michael J. North,et al.  Tutorial on agent-based modelling and simulation , 2005, Proceedings of the Winter Simulation Conference, 2005..

[25]  Mario Lucic,et al.  Are GANs Created Equal? A Large-Scale Study , 2017, NeurIPS.

[26]  Dhananjay K. Gode,et al.  Allocative Efficiency of Markets with Zero-Intelligence Traders: Market as a Partial Substitute for Individual Rationality , 1993, Journal of Political Economy.

[27]  R. Cont.  Empirical properties of asset returns: stylized facts and statistical issues , 2001 .

[28]  Yuanbo Wang,et al.  Model-based Reinforcement Learning for Predictions and Control for Limit Order Books , 2019, ArXiv.

[29]  R. Sakia.  The Box-Cox transformation technique: a review , 1992 .

[30]  Michael Wooldridge,et al.  Agent-Based Modeling for Complex Financial Systems , 2018, IEEE Intelligent Systems.