EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry

Muhammad Idrees iD, Maqbool Hussain Sial, Najam Ul Hassan

PLOS ONE · 18.03.2025 · 20 (3) · e0319679

DOI: 10.1371/journal.pone.0319679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 18.03.2025. Verfasst von Muhammad Idrees und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Economics and Quantitative Methods, Dr. Hasan Murad School of Management (HSM), University of Management and Technology (UMT), Lahore, …. Hauptthemen laut MEDLINE: Investments, Commerce, Models, Economic. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Stability of the economy is always a great challenge across the world, especially in under developed countries. Many researchers have contributed to forecasting the Stock Market and controlling the situation to ensure economic stability over the past several decades. For this purpose, many researchers have built various models and gained benefits. This journey continues to date and will persist for the betterment of the stock market. This study is also a part of this journey, where four learning-based models are tailored for stock price prediction. Daily business data from the Karachi Stock Exchange (100 Index), covering from February 22, 2008 to February 23, 2021, is used for training and testing these models. This paper presenting four deep learning models with different architectures, namely the Artificial Neural Network model, the Recurrent Neural Network with Attention model, the Long Short-Term Memory Network with Attention model, and the Gated Recurrent Unit with Attention model. The Long Short-Term Memory with attention model was found to be the top-performing technique for accurately predicting stock exchange prices. During the Training, Validation and Testing Sessions, we observed the R-Squared values of the proposed model to be 0.9996, 0.9980 and 0.9921, respectively, making it the best-performing model among those mentioned above.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

InvestmentsCommerceModels, EconomicForecastingNeural Networks, ComputerHumansDeep LearningLong Short Term Memory

Autor:innen und Institutionen

  • Department of Economics and Quantitative Methods, Dr. Hasan Murad School of Management (HSM), University of Management and Technology (UMT), Lahore, Pakistan.
  • Department of Economics, Thal University, Bhakkar, Pakistan.

ORCID-Profile: Muhammad Idrees

Zitieren

APA

Idrees, M., Hussain Sial, M., & Ul Hassan, N. (2025). Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry. PLOS ONE, 20(3), e0319679. https://doi.org/10.1371/journal.pone.0319679

Vancouver

Idrees M, Hussain Sial M, Ul Hassan N. Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry. PLOS ONE. 2025;20(3):e0319679. doi:10.1371/journal.pone.0319679

BibTeX
@article{Idrees2025,
  author = {Idrees, Muhammad and Hussain Sial, Maqbool and Ul Hassan, Najam},
  title = {Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {3},
  pages = {e0319679},
  doi = {10.1371/journal.pone.0319679}
}
Kostenlos starten →