Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)

<Previous Article In Volume
Next Article In Volume>

Stock Trading Strategy Developing Based on Reinforcement Learning

Authors
Zeyu Xia1, Mingde Shi2, Changle Lin3, 4, *
1Department of Economics, Shenzhen University, Shenzhen, China
2Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China
3China Aerospace Academy of Systems Science and Engineering, Beijing, China
4Institute for Interdisciplinary Information Core Technology, Xi’an, China
*Corresponding author. Email: changlelin@tsinghua.edu.cn
Corresponding Author
Changle Lin
Available Online 10 August 2023.
DOI
10.2991/978-94-6463-198-2_18How to use a DOI?
Keywords
Reinforcement Learning; PPO Algorithm; Stock Trading; Introduction
Abstract

Reinforcement learning has achieved superhuman performance on many sequential decision-making problems, but only very few works are done on applying reinforcement learning to market trading. In this study, we take the stock trading problem as an Markov decision process, and applied PPO algorithm to solve the problem on the Dow Jones 30 stocks for the past 10 years. Our reinforcement learning agent is able to achieve significantly higher returns and higher Sharpe ratio than the broader market index on the test dataset of about a year. By adjusting the reward function of the PPO agent, we found that agents with appropriate risk aversion properties can achieve even higher Sharpe ratio than the risk-neutral agents.

Copyright
© 2023 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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
10 August 2023
ISBN
10.2991/978-94-6463-198-2_18
ISSN
2589-4900
DOI
10.2991/978-94-6463-198-2_18How to use a DOI?
Copyright
© 2023 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.

Cite this article

risenwbib
TY  - CONF
AU  - Zeyu Xia
AU  - Mingde Shi
AU  - Changle Lin
PY  - 2023
DA  - 2023/08/10
TI  - Stock Trading Strategy Developing Based on Reinforcement Learning
BT  - Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
PB  - Atlantis Press
SP  - 156
EP  - 164
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-198-2_18
DO  - 10.2991/978-94-6463-198-2_18
ID  - Xia2023
ER  -