Towards realistic market simulations

Coletta, Andrea; Prata, Matteo; Conti, M.; Mercanti, Emanuele; Bartolini, Novella; Moulin, Aymeric; Vyetrenko, Svitlana; Balch, Tucker

doi:10.1145/3490354.3494411

Cited by 15 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, accurately modeling the full market impact of high-frequency trading in LOB markets in a data-driven approach is an interesting direction for future research and would allow evaluating strategies with larger order sizes. Recent attempts in this vein have used agent-based models (Byrd et al, 2020b ) or generative models (Coletta et al, 2021 , 2022 , 2023 ).…”

Section: Discussionmentioning

confidence: 99%

Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets

Nagy,

Calliess,

Zohren

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

We employ deep reinforcement learning (RL) to train an agent to successfully translate a high-frequency trading signal into a trading strategy that places individual limit orders. Based on the ABIDES limit order book simulator, we build a reinforcement learning OpenAI gym environment and utilize it to simulate a realistic trading environment for NASDAQ equities based on historic order book messages. To train a trading agent that learns to maximize its trading return in this environment, we use Deep Dueling Double Q-learning with the APEX (asynchronous prioritized experience replay) architecture. The agent observes the current limit order book state, its recent history, and a short-term directional forecast. To investigate the performance of RL for adaptive trading independently from a concrete forecasting algorithm, we study the performance of our approach utilizing synthetic alpha signals obtained by perturbing forward-looking returns with varying levels of noise. Here, we find that the RL agent learns an effective trading strategy for inventory management and order placing that outperforms a heuristic benchmark trading strategy having access to the same signal.

show abstract

Section: Discussionmentioning

confidence: 99%

Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets

Nagy,

Calliess,

Zohren

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…well as deep generative models such as GANs and variational autoencoders (VAEs) [6,12,43]. These methods provide higher accuracy than traditional generative approaches but are more challenging to reproduce out-of-distribution or long-tail events such as those experienced during the COVID-19 pandemic or the global financial crises of 2008.…”

Section: Timementioning

confidence: 99%

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Stillman,

Baggott,

Lyon

et al. 2023

4th ACM International Conference on AI in Finance

View full text Add to dashboard Cite

The ability to construct a realistic simulator of financial exchanges, including reproducing the dynamics of the limit order book, can give insight into many counterfactual scenarios, such as a flash crash, a margin call, or changes in macroeconomic outlook. In recent years, agent-based models have been developed that reproduce many features of an exchange, as summarised by a set of stylised facts and statistics. However, the ability to calibrate simulators to a specific period of trading remains an open challenge. In this work, we develop a novel approach to the calibration of market simulators by leveraging recent advances in deep learning, specifically using neural density estimators and embedding networks. We demonstrate that our approach is able to correctly identify high probability parameter sets, both when applied to synthetic and historical data, and without reliance on manually selected or weighted ensembles of stylised facts.

show abstract

“…Recent work shows that highly complex environments with multiple autonomous agents can be successfully simulated by learning a unique world-policy able to mimic all the agents (Ha and Schmidhuber, 2018;Coletta et al, 2021;. To truthfully simulate the real world and the agent interactions, these models have to learn and impersonate multiple heterogeneous behaviors upon different input from the environment.…”

Section: World Policymentioning

confidence: 99%

Learning to simulate realistic limit order book markets from data as a World Agent

Coletta

Moulin²,

Vyetrenko

et al. 2022

Proceedings of the Third ACM International Conference on AI in Finance

Self Cite

View full text Add to dashboard Cite

Multi-agent market simulators usually require careful calibration to emulate real markets, which includes the number and the type of agents. Poorly calibrated simulators can lead to misleading conclusions, potentially causing severe loss when employed by investment banks, hedge funds, and traders to study and evaluate trading strategies. In this paper, we propose a world model simulator that accurately emulates a limit order book market -it requires no agent calibration but rather learns the simulated market behavior directly from historical data. Traditional approaches fail short to learn and calibrate trader population, as historical labeled data with details on each individual trader strategy is not publicly available. Our approach proposes to learn a unique "world" agent from historical data. It is intended to emulate the overall trader population, without the need of making assumptions about individual market agent strategies. We implement our world agent simulator models as a Conditional Generative Adversarial Network (CGAN), as well as a mixture of parametric distributions, and we compare our models against previous work. Qualitatively and quantitatively, we show that the proposed approaches consistently outperform previous work, providing more realism and responsiveness.

show abstract

Towards realistic market simulations

Cited by 15 publications

References 14 publications

Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets

Asynchronous Deep Double Dueling Q-learning for trading-signal execution in limit order book markets

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Learning to simulate realistic limit order book markets from data as a World Agent

Contact Info

Product

Resources

About