arXiv Open Access 2025

Can Artificial Intelligence Trade the Stock Market?

Jędrzej Maskiewicz Paweł Sakowski

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

q-fin.TR cs.LG q-fin.CP

Penulis (2)

Jędrzej Maskiewicz

Paweł Sakowski

Format Sitasi

APA MLA BibTeX

Maskiewicz, J., Sakowski, P. (2025). Can Artificial Intelligence Trade the Stock Market?. https://arxiv.org/abs/2506.04658

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓