Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators
This work addresses the need for robust testing of trading strategies in electronic markets by enabling simulators to represent varied scenarios, though it is incremental in improving calibration techniques.
The paper tackles the problem of calibrating multi-agent market simulators to capture different market regimes, such as ordinary and stressed markets, by proposing a two-step method using a GAN with self-attention to distinguish real and fake time series and optimize simulator parameters, resulting in effective experimental outcomes.
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.