Saved in:
Bibliographic Details
Main Authors: Wang, Ziyi, Ventre, Carmine, Polukarov, Maria
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16589
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915457488912384
author Wang, Ziyi
Ventre, Carmine
Polukarov, Maria
author_facet Wang, Ziyi
Ventre, Carmine
Polukarov, Maria
contents We advance market-making strategies by integrating Adversarial Reinforcement Learning (ARL), Hawkes Processes, and variable volatility levels while also expanding the action space available to market makers (MMs). To enhance the adaptability and robustness of these strategies -- which can quote always, quote only on one side of the market or not quote at all -- we shift from the commonly used Poisson process to the Hawkes process, which better captures real market dynamics and self-exciting behaviors. We then train and evaluate strategies under volatility levels of 2 and 200. Our findings show that the 4-action MM trained in a low-volatility environment effectively adapts to high-volatility conditions, maintaining stable performance and providing two-sided quotes at least 92\% of the time. This indicates that incorporating flexible quoting mechanisms and realistic market simulations significantly enhances the effectiveness of market-making strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARL-Based Multi-Action Market Making with Hawkes Processes and Variable Volatility
Wang, Ziyi
Ventre, Carmine
Polukarov, Maria
Trading and Market Microstructure
Artificial Intelligence
General Economics
Economics
We advance market-making strategies by integrating Adversarial Reinforcement Learning (ARL), Hawkes Processes, and variable volatility levels while also expanding the action space available to market makers (MMs). To enhance the adaptability and robustness of these strategies -- which can quote always, quote only on one side of the market or not quote at all -- we shift from the commonly used Poisson process to the Hawkes process, which better captures real market dynamics and self-exciting behaviors. We then train and evaluate strategies under volatility levels of 2 and 200. Our findings show that the 4-action MM trained in a low-volatility environment effectively adapts to high-volatility conditions, maintaining stable performance and providing two-sided quotes at least 92\% of the time. This indicates that incorporating flexible quoting mechanisms and realistic market simulations significantly enhances the effectiveness of market-making strategies.
title ARL-Based Multi-Action Market Making with Hawkes Processes and Variable Volatility
topic Trading and Market Microstructure
Artificial Intelligence
General Economics
Economics
url https://arxiv.org/abs/2508.16589