A1 Journal article (refereed), original research

Deep Reinforcement Learning Agent for S&P 500 Stock Selection


Open Access publication

Publication Details
Authors: Huotari Tommi, Savolainen Jyrki, Collan Mikael
Publisher: MDPI
Publication year: 2020
Language: English
Related Journal or Series Information: Axioms
Volume number: 9
Issue number: 4
Start page: 1
End page: 15
Number of pages: 15
ISSN: 2075-1680
eISSN: 2075-1680
JUFO-Level of this publication: 1
Open Access: Open Access publication

Abstract

This study investigated the performance of a trading agent based on a convolutional neural
network model in portfolio management. The results showed that with real-world data the agent
could produce relevant trading results, while the agent’s behavior corresponded to that of a high-risk
taker. The data used were wide in comparison with earlier reported research and was based on the
full set of the S&P 500 stock data for twenty-one years supplemented with selected financial ratios.
The results presented are new in terms of the size of the data set used and with regards to the model
used. The results provide direction and oer insight into how deep learning methods may be used in
constructing automatic trading systems.


Research Areas

Last updated on 2021-16-03 at 12:47