Comparison of Deep Reinforcement Learning Algorithms for Trading Strategy

DOI

10.2991/978-94-6463-370-2_2How to use a DOI?

Keywords

Reinforcement learning; Deep learning; Trading strategy

Abstract

A stock trading strategy refers to a structured approach used to make informed decisions in buying, selling, or holding stocks in financial markets. These strategies play a crucial role in maximizing returns while managing risk. Over the years, trading strategies have transitioned from being expert-driven, time-intensive approaches to incorporating machine learning algorithms that process vast amounts of historical data. Stock trading strategies have evolved from expert-driven approaches to incorporating machine learning algorithms and, more recently, artificial intelligence and deep learning techniques. This paper delves into the utilization of deep reinforcement learning in trade. It presents an overview of Deep Reinforcement Learning (DRL) principles and their relevance to trading, followed by an exploration of five specific machine-learning models employed in trading strategies. Each model is detailed in terms of its characteristics, principles, advantages, and limitations. Additionally, this paper discusses evaluation metrics and provides a brief insight into potential result disparities within the same stock. The discussion section analyzes the strengths and weaknesses of the presented models and highlights their potential. The conclusion summarizes the methods employed and the results observed and suggests avenues for future research and development in utilizing DRL for trading strategies.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiaoyang Jiang
PY  - 2024
DA  - 2024/02/14
TI  - Comparison of Deep Reinforcement Learning Algorithms for Trading Strategy
BT  - Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023)
PB  - Atlantis Press
SP  - 4
EP  - 14
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-370-2_2
DO  - 10.2991/978-94-6463-370-2_2
ID  - Jiang2024
ER  -