Forecasting Short-Term FTSE Bursa Malaysia Using WEKA

Nurhuda Nizar, Ahmad Danial Zainudin, Ali Albada and Chua Mei Shan

Information Management and Business Review, 2024, vol. 16, issue 2, 104-114

Abstract: This study investigates the use of machine learning methods, specifically utilizing the WEKA software, to predict stock prices of the FTSE Bursa Malaysia Kuala Lumpur Composite Index (KLCI). Two algorithms, Sequential Minimal Optimization Regression (SMOreg) and Multilayer perceptron (MLP), were employed for data analysis. Historical data from January 3, 2023, to December 29, 2023, was used to forecast open, high low, and close prices for ten days. Results from both algorithms were compared, with SMOreg proving to be more accurate than MLP for the dataset. However, it's important to note that further exploration of different forecasting algorithms may lead to even more precise results in the future. The findings of this analysis hold significant implications for investors, as they can use the insights gained to inform their investment strategies. By leveraging machine learning techniques like SMOreg within the WEKA framework, investors can potentially make more informed decisions regarding their stock market investments, leading to improved portfolio performance and risk management.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://ojs.amhinternational.com/index.php/imbr/article/view/3773/2471 (application/pdf)
https://ojs.amhinternational.com/index.php/imbr/article/view/3773 (text/html)

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:rnd:arimbr:v:16:y:2024:i:2:p:104-114

DOI: 10.22610/imbr.v16i2(I)S.3773

Access Statistics for this article

More articles in Information Management and Business Review from AMH International
Bibliographic data for series maintained by Muhammad Tayyab ().