Using CNN to Model Stock Prices

Mitja Steinbacher (), Matej Steinbacher () and Matjaz Steinbacher ()
Additional contact information
Mitja Steinbacher: Faculty of Law and Business Studies, Catholic Institute
Matej Steinbacher: Pixlifai
Matjaz Steinbacher: Fund for Financing the Decommissioning of the Krško Nuclear Power Plant and Disposal of Radioactive Waste

Computational Economics, 2025, vol. 66, issue 6, No 30, 5299-5340

Abstract: Abstract The paper applies Convolutional Neural Networks to examine whether and to what extent closing stock prices can be predicted during the opening hour of a trading day. In particular, the MobileNet-V2 architecture was implemented, which transforms the financial time series into an image classification problem. We used daily data in a 5-minute time interval of the 1000 largest listings in Nasdaq by market capitalization. Results show that according to a standard performance measures, the MobileNet-V2 achieved a high prediction accuracy and outperformed several alternative deep learning algorithms.

Keywords: Convolutional neural networks; MobileNet-V2; Deep learning; Image classification; Stock price prediction (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-025-10887-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:66:y:2025:i:6:d:10.1007_s10614-025-10887-3

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-025-10887-3

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().