Can Artificial Intelligence Trade the Stock Market?
By: Jędrzej Maskiewicz, Paweł Sakowski
Potential Business Impact:
Makes computers trade stocks smarter and safer.
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.
Similar Papers
Risk-Aware Deep Reinforcement Learning for Dynamic Portfolio Optimization
Portfolio Management
Teaches computers to invest money safely.
A Practical Introduction to Deep Reinforcement Learning
Machine Learning (CS)
Teaches computers to learn and make smart choices.
Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy
Trading & Market Microstructure
Teaches computers to make money trading stocks.