Deep Reinforcement Learning Agent for S&P 500 Stock Selection

Deep Reinforcement Learning Agent for S&P 500 Stock Selection

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 d...

Full description

Bibliographic Details
Main Authors: Tommi Huotari, Jyrki Savolainen, Mikael Collan
Format: Article
Language:English
Published: MDPI AG 2020-11-01
Series:Axioms
Subjects:
deep reinforcement learning
portfolio selection
convolutional neural network
feature selection
trading agent
Online Access:https://www.mdpi.com/2075-1680/9/4/130
id doaj-01831bc8b43a42c79133cfa375b424b8
record_format Article
spelling doaj-01831bc8b43a42c79133cfa375b424b82020-11-25T04:04:27ZengMDPI AGAxioms2075-16802020-11-01913013010.3390/axioms9040130Deep Reinforcement Learning Agent for S&P 500 Stock SelectionTommi Huotari0Jyrki Savolainen1Mikael Collan2School of Business and Management, LUT University, 53850 Lappeenranta, FinlandSchool of Business and Management, LUT University, 53850 Lappeenranta, FinlandSchool of Business and Management, LUT University, 53850 Lappeenranta, FinlandThis 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 offer insight into how deep learning methods may be used in constructing automatic trading systems.https://www.mdpi.com/2075-1680/9/4/130deep reinforcement learningportfolio selectionconvolutional neural networkfeature selectiontrading agent
collection DOAJ
language English
format Article
sources DOAJ
author Tommi Huotari
Jyrki Savolainen
Mikael Collan
spellingShingle Tommi Huotari
Jyrki Savolainen
Mikael Collan
Deep Reinforcement Learning Agent for S&P 500 Stock Selection
Axioms
deep reinforcement learning
portfolio selection
convolutional neural network
feature selection
trading agent
author_facet Tommi Huotari
Jyrki Savolainen
Mikael Collan
author_sort Tommi Huotari
title Deep Reinforcement Learning Agent for S&P 500 Stock Selection
title_short Deep Reinforcement Learning Agent for S&P 500 Stock Selection
title_full Deep Reinforcement Learning Agent for S&P 500 Stock Selection
title_fullStr Deep Reinforcement Learning Agent for S&P 500 Stock Selection
title_full_unstemmed Deep Reinforcement Learning Agent for S&P 500 Stock Selection
title_sort deep reinforcement learning agent for s&p 500 stock selection
publisher MDPI AG
series Axioms
issn 2075-1680
publishDate 2020-11-01
description 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 offer insight into how deep learning methods may be used in constructing automatic trading systems.
topic deep reinforcement learning
portfolio selection
convolutional neural network
feature selection
trading agent
url https://www.mdpi.com/2075-1680/9/4/130
work_keys_str_mv AT tommihuotari deepreinforcementlearningagentforsp500stockselection
AT jyrkisavolainen deepreinforcementlearningagentforsp500stockselection
AT mikaelcollan deepreinforcementlearningagentforsp500stockselection
_version_ 1724436722012389376

Similar Items