Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making

In the realm of global Science, Technology, Engineering, and Mathematics (STEM) education, the declining enrollment in advanced mathematics courses poses a substantial challenge to the development of a robust STEM workforce and its role in sustainable economic growth. The study’s primary objectives...

Full description

Bibliographic Details
Main Authors: Chuan, Zun Liang, Japashov, Nursultan, Yuan, Soon Kien, Tan, Wei Qing, Noriszura, Ismail
Format: Article
Language:English
Published: Universiti Kebangsaan Malaysia 2024
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/42189/
http://umpir.ump.edu.my/id/eprint/42189/1/Chuan%20et%20al.%20%282024%29.pdf
_version_ 1848826544418455552
author Chuan, Zun Liang
Japashov, Nursultan
Yuan, Soon Kien
Tan, Wei Qing
Noriszura, Ismail
author_facet Chuan, Zun Liang
Japashov, Nursultan
Yuan, Soon Kien
Tan, Wei Qing
Noriszura, Ismail
author_sort Chuan, Zun Liang
building UMP Institutional Repository
collection Online Access
description In the realm of global Science, Technology, Engineering, and Mathematics (STEM) education, the declining enrollment in advanced mathematics courses poses a substantial challenge to the development of a robust STEM workforce and its role in sustainable economic growth. The study’s primary objectives were to identify the determinants that impacted urban upper-secondary students' enrolment in Additional Mathematics within the Kuantan District, Pahang, Malaysia, and to develop a novel modified stacked ensemble statistical learning-based algorithm based on these determinants, following the CRISP-DM data science methodology. To pursue these objectives, this study collected and analyzed 389 responses from the first-batch urban upper-secondary students in the Kuantan District who had enrolled in the newly revised Standard Based Curriculum for Secondary Schools (KSSM’s) Additional Mathematics syllabus, utilizing a modified research questionnaire and a one-stage cluster sampling technique. The findings revealed that determinants such as education disciplines, ethnicity, gender, mathematics self-efficacy, peer influence, and teacher influence had significantly impacted students' decisions to enroll in Additional Mathematics. Moreover, the introduction of the novel modified stacked ensemble statistical learning-based algorithm had improved predictive accuracy compared to traditional dichotomous logistic regression algorithms on average, particularly at optimal training-to-test ratios of 70:30, 80:20, and 90:10. These insights were valuable for shaping educational policy and practice, emphasizing the importance of promoting STEM education initiatives and encouraging educators and counselors to empower students to pursue STEM careers while actively promoting gender equality within STEM fields.
first_indexed 2025-11-15T03:46:30Z
format Article
id ump-42189
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:46:30Z
publishDate 2024
publisher Universiti Kebangsaan Malaysia
recordtype eprints
repository_type Digital Repository
spelling ump-421892024-08-12T04:01:39Z http://umpir.ump.edu.my/id/eprint/42189/ Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making Chuan, Zun Liang Japashov, Nursultan Yuan, Soon Kien Tan, Wei Qing Noriszura, Ismail H Social Sciences (General) HA Statistics QA Mathematics In the realm of global Science, Technology, Engineering, and Mathematics (STEM) education, the declining enrollment in advanced mathematics courses poses a substantial challenge to the development of a robust STEM workforce and its role in sustainable economic growth. The study’s primary objectives were to identify the determinants that impacted urban upper-secondary students' enrolment in Additional Mathematics within the Kuantan District, Pahang, Malaysia, and to develop a novel modified stacked ensemble statistical learning-based algorithm based on these determinants, following the CRISP-DM data science methodology. To pursue these objectives, this study collected and analyzed 389 responses from the first-batch urban upper-secondary students in the Kuantan District who had enrolled in the newly revised Standard Based Curriculum for Secondary Schools (KSSM’s) Additional Mathematics syllabus, utilizing a modified research questionnaire and a one-stage cluster sampling technique. The findings revealed that determinants such as education disciplines, ethnicity, gender, mathematics self-efficacy, peer influence, and teacher influence had significantly impacted students' decisions to enroll in Additional Mathematics. Moreover, the introduction of the novel modified stacked ensemble statistical learning-based algorithm had improved predictive accuracy compared to traditional dichotomous logistic regression algorithms on average, particularly at optimal training-to-test ratios of 70:30, 80:20, and 90:10. These insights were valuable for shaping educational policy and practice, emphasizing the importance of promoting STEM education initiatives and encouraging educators and counselors to empower students to pursue STEM careers while actively promoting gender equality within STEM fields. Universiti Kebangsaan Malaysia 2024 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/42189/1/Chuan%20et%20al.%20%282024%29.pdf Chuan, Zun Liang and Japashov, Nursultan and Yuan, Soon Kien and Tan, Wei Qing and Noriszura, Ismail (2024) Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making. Akademika, 94 (2). pp. 232-251. ISSN 0126-5008. (Published) https://doi.org/10.17576/akad-2024-9402-13 10.17576/akad-2024-9402-13
spellingShingle H Social Sciences (General)
HA Statistics
QA Mathematics
Chuan, Zun Liang
Japashov, Nursultan
Yuan, Soon Kien
Tan, Wei Qing
Noriszura, Ismail
Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title_full Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title_fullStr Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title_full_unstemmed Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title_short Analyzing enrolment patterns: Modified stacked ensemble statistical learning-based approach to educational decision-making
title_sort analyzing enrolment patterns: modified stacked ensemble statistical learning-based approach to educational decision-making
topic H Social Sciences (General)
HA Statistics
QA Mathematics
url http://umpir.ump.edu.my/id/eprint/42189/
http://umpir.ump.edu.my/id/eprint/42189/
http://umpir.ump.edu.my/id/eprint/42189/
http://umpir.ump.edu.my/id/eprint/42189/1/Chuan%20et%20al.%20%282024%29.pdf