Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators

In electronic trading markets often only the price or volume time series, that result from interaction of multiple market participants, are directly observable. In order to test trading strategies before deploying them to real-time trading, multi-agent market environments calibrated so that the time series that result from interaction of simulated agents resemble historical are often used. To ensure adequate testing, one must test trading strategies in a variety of market scenarios – which includes both scenarios that represent ordinary market days as well as stressed markets (most recently observed due to the beginning of COVID pandemic). In this paper, we address the problem of multi-agent simulator parameter calibration to allow simulator capture characteristics of different market regimes. We propose a novel two-step method to train a discriminator that is able to distinguish between “real” and “fake” price and volume time series as a part of GAN with self-attention, and then utilize it within an optimization framework to tune parameters of a simulator model with known agent archetypes to represent a market scenario. We conclude with experimental results that demonstrate effectiveness of our method.

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

[2]  Emanuele Ghelfi,et al.  A Survey on GANs for Anomaly Detection , 2019, ArXiv.

[3]  Gunnar Rätsch,et al.  Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs , 2017, ArXiv.

[4]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[5]  Julien Rabin,et al.  Detecting Overfitting of Deep Generative Networks via Latent Recovery , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Svitlana Vyetrenko,et al.  Risk-Sensitive Compact Decision Trees for Autonomous Execution in Presence of Simulated Market Response , 2019, ArXiv.

[8]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[9]  See-Kiong Ng,et al.  Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series , 2018, ArXiv.

[10]  Alexander Outkin,et al.  A NASDAQ Market Simulation - Insights on a Major Market from the Science of Complex Adaptive Systems , 2007, Complex Systems and Interdisciplinary Science.

[11]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[12]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[13]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[14]  M. M. Gabr,et al.  Time Series Classification , 2013 .

[15]  J. Bouchaud,et al.  Trades, Quotes and Prices: Financial Markets Under the Microscope , 2018 .

[16]  Saúl Alonso-Monsalve,et al.  Image-Based Model Parameter Optimization Using Model-Assisted Generative Adversarial Networks , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

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