Interactive Agent-Based Simulators are used to evaluate trading strategies before their adoption in real markets. However, it is impossible to exactly understand traders’ behaviors, and these approaches do not produce accurate results.
A recent paper on arXiv.org proposes a GAN-based framework that is able to learn an abstract representation of the market that can also react to the observed market state. Conditional Generative Adversarial Network (CGAN), trained on real historical data, captures the market’s behavior as a whole arising from the activity of different participants. Synthetic market data is generated as a function of the features observed from the current market situation.
The approach guarantees both realism of the produced market trend and market responsiveness to the experimental agent’s activity. It is shown that the architecture outperforms existing approaches by exhibiting more realistic properties.
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.
Research paper: Coletta, A., “Towards Realistic Market Simulations: a Generative Adversarial Networks Approach”, 2021. Link: https://arxiv.org/abs/2110.13287