A Simple Reinforcement Learning Algorithm for Stock Trading

Author:

Abstract
In recent years, the use of machine learning techniques in financial markets, particularly in stock trading, has garnered considerable attention from both academia and practitioners. Researchers have examined various supervised and unsupervised learning techniques for forecasting stock price movement and making market decisions. The purpose of this study is to examine the application of reinforcement learning techniques to stock trading. We evaluate this approach using real-world stock datasets, and our results suggest that reinforcement learning holds a great deal of promise for stock trading decision-making. We compare our trading algorithm's Sharpe ratio values to other studies and find that the performance of our algorithm is comparable to more complex approaches in some cases.

This publication has 13 references indexed in Scilit: