Application of Deep Q-Network in Portfolio Management

Ziming Gao, Yuan Gao, Yi Hu, Zhengyong Jiang, Jionglong Su

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

32 Citations (Scopus)

Abstract

Machine Learning algorithms and Neural Networks are widely applied to many different areas such as stock market prediction, facial recognition and automatic machine translation. This paper introduces a novel strategy based on the classic Deep Reinforcement Learning algorithm, Deep QNetwork, for stock market portfolio management. It is a type of deep neural network which is optimized by Q Learning. To adapt the Deep Q-Network for stock market production, we first discretize the action space so that portfolio management becomes a problem that Deep Q-Network can solve. Following this, we combine the Convolutional Neural Network and dueling Q-Net to enhance the recognition ability of the algorithm. We choose five low-relevant American stocks to test our model. It is found that the Deep Q-Network based strategy outperforms the ten other traditional strategies. The profit of Deep Q-Network algorithm is 30% more than the profit of other strategies. Moreover, the Sharpe ratio and Max Drawdown demonstrates that the risk of policy associated with Deep Q-Network is the lowest.

Original languageEnglish
Title of host publication2020 5th IEEE International Conference on Big Data Analytics, ICBDA 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages268-275
Number of pages8
ISBN (Electronic)9781728141114
DOIs
Publication statusPublished - May 2020
Event5th IEEE International Conference on Big Data Analytics, ICBDA 2020 - Xiamen, China
Duration: 8 May 202011 May 2020

Publication series

Name2020 5th IEEE International Conference on Big Data Analytics, ICBDA 2020

Conference

Conference5th IEEE International Conference on Big Data Analytics, ICBDA 2020
Country/TerritoryChina
CityXiamen
Period8/05/2011/05/20

Keywords

  • Q learning
  • convolutional neural network
  • portfolio management

Fingerprint

Dive into the research topics of 'Application of Deep Q-Network in Portfolio Management'. Together they form a unique fingerprint.

Cite this