Can Artificial Intelligence Trade the Stock Market?
Trading and Market Microstructure
2025-06-06 v1 Machine Learning
Computational Finance
Abstract
The paper explores the use of Deep Reinforcement Learning (DRL) in stock market trading, focusing on two algorithms: Double Deep Q-Network (DDQN) and Proximal Policy Optimization (PPO) and compares them with Buy and Hold benchmark. It evaluates these algorithms across three currency pairs, the S&P 500 index and Bitcoin, on the daily data in the period of 2019-2023. The results demonstrate DRL's effectiveness in trading and its ability to manage risk by strategically avoiding trades in unfavorable conditions, providing a substantial edge over classical approaches, based on supervised learning in terms of risk-adjusted returns.
Cite
@article{arxiv.2506.04658,
title = {Can Artificial Intelligence Trade the Stock Market?},
author = {Jędrzej Maskiewicz and Paweł Sakowski},
journal= {arXiv preprint arXiv:2506.04658},
year = {2025}
}