Time-varying neural network for stock return prediction

Steven Y. K. Wong*, Jennifer S. K. Chan, Lamiae Azizi, Richard Y. D. Xu

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

1 Citation (Scopus)


We consider the problem of neural network training in a time-varying context. Machine learning algorithms have excelled in problems that do not change over time. However, problems encountered in financial markets are often time varying. We propose the online early stopping algorithm and show that a neural network trained using this algorithm can track a function changing with unknown dynamics. We compare the proposed algorithm to current approaches on predicting monthly US stock returns and show its superiority. We also show that prominent factors (such as the size and momentum effects) and industry indicators exhibit time-varying predictive power on stock returns. We find that during market distress, industry indicators experience an increase in importance at the expense of firm level features. This indicates that industries play a role in explaining stock returns during periods of heightened risk.

Original languageEnglish
Pages (from-to)3-18
Number of pages16
JournalIntelligent Systems in Accounting, Finance and Management
Issue number1
Publication statusPublished - Jan 2022
Externally publishedYes

Scopus Subject Areas

  • Business, Management and Accounting(all)
  • Finance

User-Defined Keywords

  • deep learning
  • neural network
  • online learning
  • return prediction
  • time-varying


Dive into the research topics of 'Time-varying neural network for stock return prediction'. Together they form a unique fingerprint.

Cite this