General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Managing Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • Average Days from Submission to Acceptance: 192 days
    • E-mail: ijcte@iacsitp.com
    • Journal Metrics:

    • SCImago Journal & Country Rank
Editor-in-chief
Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2024 Vol.16(2): 44-54
DOI: 10.7763/IJCTE.2024.V16.1353

Adaptive Model Selection in Stock Market Prediction: A Modular and Scalable Big Data Analytics Approach

MohammadEhsan Akhavanpour * and Saeed Samet
School of Computer Science, University of Windsor, Windsor, ON, Canada
Email: akhavanm@uwindsor.ca (M.A.); saeed.samet@uwindsor.ca (S.S.)
*Corresponding author

Manuscript received January 10, 2024; revised February 6, 2024; accepted April 7, 2024; published May 10, 2024

Abstract—This paper introduces an innovative architecture integrating Apache Kafka and microservices to enhance real-time stock market prediction. Our approach dynamically selects the most effective predictive model based on current market conditions, ensuring consistent accuracy. The key research method involves deploying Apache Kafka for real-time data streaming, coupled with a microservices framework to maintain scalability and adaptability. Our methodology includes a thorough evaluation of various machine learning models (specifically focusing on R2, the coefficient of determination, as the metric) to ascertain their performance across different market scenarios. The results demonstrate the architecture’s ability to handle high data volume and velocity, while accurately adapting to market changes. The adaptability is evidenced by the varying performance of models like Convolutional Neural Network (CNN), Gate Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) across different entities such as Royal Bank of Canada, Google, and EUR/USD, with the system successfully identifying the most suitable model in real-time. This architecture not only provides a scalable solution for stock market prediction but also sets the foundation for future exploration in other real-time data-intensive domains.

Keywords—Apache Kafka, microservices architecture, real-time model switching, financial market prediction

[PDF]

Cite: MohammadEhsan Akhavanpour and Saeed Samet, "Adaptive Model Selection in Stock Market Prediction: A Modular and Scalable Big Data Analytics Approach," International Journal of Computer Theory and Engineering, vol. 16, no. 2, pp. 44-54, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).


Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.