Profit-based deep architecture with integration of reinforced data selector to enhance trend-following strategy

Yang LI*, Zibin ZHENG, Hong-ning DAI, Raymond Chi-Wing WONG, Haoran XIE

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)

Abstract

Despite the popularity of trend-following strategies in financial markets, they often lack adaptability to the emerging varied markets. Recently, deep learning (DL) methods demonstrate the effectiveness in stock-market analysis. Thus, the application of DL methods to enhance trend-following strategies has received substantial attention. However, there are two key challenges to be solved before the adoption of DL methods in enhancing trend-following strategies: (1) how to design an effective data selector to include more related data? (2) how to design a profit-based model to enhance strategies? To address these two challenges, this paper contributes to a new framework, namely profit-based deep architecture with the integration of reinforced data selector (PDA-RDS) to improve the effectiveness of DL methods. In particular, profit-based deep architecture (PDA) integrates a dynamic profit weight and a focal loss function to obtain high profits. In addition, reinforced data selector (RDS) is constructed to select high-quality training samples and a training-aware immediate reward is designated to improve the effectiveness of RDS. Extensive experiments on both U.S. and China stock-market datasets demonstrate that PDA-RDS outperforms the state-of-the-art baseline methods in terms of higher cumulative percentage rate and average percentage rate, both of which are crucial to investment strategies.
Original languageEnglish
JournalWorld Wide Web
DOIs
Publication statusE-pub ahead of print - 14 Oct 2022

Bibliographical note

Funding Information:
The research is supported by the Key-Area Research and Development Program of Guangdong Province (2020B010165003), the National Natural Science Foundation of China under project (62032025), and the Technology Program of Guangzhou, China (202103050004), Faculty Research Grants (DB22A5 and DB22B7) of Lingnan University, Hong Kong.

Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Keywords

  • Data selection
  • Deep learning
  • Reinforcement learning
  • Transfer learning
  • Trend-following strategy

Fingerprint

Dive into the research topics of 'Profit-based deep architecture with integration of reinforced data selector to enhance trend-following strategy'. Together they form a unique fingerprint.

Cite this