Can Artificial Intelligence Trade the Stock Market?

TL;DR

This paper investigates the application of Deep Reinforcement Learning algorithms, specifically DDQN and PPO, to stock and cryptocurrency trading, demonstrating their potential to outperform traditional methods in risk-adjusted returns.

Contribution

It introduces the use of DRL algorithms in trading across multiple assets and compares their performance with classical approaches, highlighting their effectiveness.

Findings

DRL algorithms outperform buy-and-hold in risk-adjusted returns

DRL effectively manages risk by avoiding unfavorable trades

DRL shows promise across various asset classes

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.