Home/Journal of Artificial Intelligence in Engineering Practice/Article Record
Peer-Reviewed Article March 31, 2024

Enhancing Stock Price Prediction Accuracy Using ARIMA and Advanced Greylag Goose Optimizer Algorithm

Are you an author of this work?Link to your sovereign AfriScholar profile
Published in: Journal of Artificial Intelligence in Engineering Practice
Publisher: The Scientific Association for Studies and Applied Research • Egypt • 3009-7452 • 3009-7002
DOI: https://doi.org/10.21608/jaiep.2024.355004

Abstract

This paper applies ARIMA and the Greylag Goose Optimizer (GGO) algorithm, among others, for pre-trending the stock market prediction. This study aims to improve stock price forecasting using proper feature selection methods and time series modeling. The dataset encompasses historical pricing data that was scraped from Yahoo Finance in January 2019. There were many models for feature selection applied in the data preprocessing phase, such as bGGO, bGWO, bGWO_PSO, bPSO, bWAO, bBBO, bMVO, bSBO, bGWOGA and bFA. The model's performance was judged on metrics based on average error, select size and fitness; the GGO (Greylag Goose Optimizer) algorithm had the best performance rating, with an Average error equal to 0.36455. The ARIMA model was used to predict future stock prices based on the selected features, with the lowest MSE being 0.001367831 and an RMSE of 0.0369842, evidencing powerful forecasting ability. This outcome proves the reliability of integrating feature selection approaches with ARIMA for stock price prediction; it helps improve forecast accuracy and provides valuable insights for investors and analysts. The final point indicates the importance of powerful optimization tools in decision-making.

Download Full Text PDFView at PublisherCrossref RecordCrossref XML

Verified Citation Velocity

Recorded scholarly citations in African and international peer-reviewed literature

3
Total Citations

Citations are continuously tracked and harvested across continental OJS endpoints and OpenAlex feeds.