A Multi-Model Heterogeneous Ensemble Learning Framework for Accurate Prediction and Optimization of Student Academic Performance
Keywords:
Student performance prediction, heterogeneous ensemble learning, educational data mining, machine learning frameworkAbstract
Accurate prediction of student academic performance has become a central research problem in educational data mining due to its implications for personalized learning, early intervention strategies, and institutional decision-making. Traditional single-model approaches often fail to capture the complex, nonlinear, and heterogeneous nature of educational datasets. This study proposes a multi-model heterogeneous ensemble learning framework designed to improve predictive accuracy and robustness in academic performance forecasting. The framework integrates diverse base learners and ensemble strategies to exploit complementary strengths of different classification paradigms.
Grounded in established ensemble theory and educational data mining literature (Rokach, 2010; Romero and Ventura, 2010), the proposed approach synthesizes heterogeneous model outputs using advanced aggregation mechanisms inspired by weak classifier cooperation principles (Kotsiantis and Pintelas, 2005). The study further aligns with prior findings demonstrating the effectiveness of ensemble-based prediction in student modeling contexts (Kotsiantis et al., 2010; Evangelista and Sy, 2022).
The framework is conceptually validated through comparative analysis with conventional machine learning approaches. Results indicate that heterogeneous ensemble structures improve prediction stability, reduce variance, and enhance generalization capability across diverse student datasets. The findings highlight the importance of model diversity, weighted aggregation, and adaptive voting mechanisms in educational prediction systems.
Downloads
References
1. Baba NM, Makhtar M, Fadzli SA, Awang MK. Current issues in ensemble methods and its applications. J Theor Appl Inf Technol. 2015;81(2):266–76.
2. Baker RSJD, Yacef K. The state of educational data mining in 2009: a review and future visions. J Educ Data Min. 2009;1(1):3–16.
3. Evangelista EDe, Descargar Sy B. An approach for improved students’ performance prediction using homogeneous and heterogeneous ensemble methods. Int J Electr Comput Eng. 2022;12(5):5226–35.
4. Jiawei H, Micheline K. Data Mining: Concepts and Techniques. Morgan kaufmann; 2012.
5. Kostopoulos G, Kotsiantis S, Pierrakeas C, Koutsonikos G, Grav-vanis GA. Forecasting students’ success in an open university. Int J Learning Technology. 2018;13(1):26–43.
6. Kotsiantis S, Patriarcheas K, Xenos M. A combinational incremental ensemble of classifiers as a technique for predicting students’ performance in distance education. Knowl Based Syst. 2010;23(6):529–35.
7. Kotsiantis S, Pintelas P. Local voting of weak classifiers. Int J Knowl Based Intell Eng Syst. 2005;9(3):239–48.
8. Large J, Lines J, Bagnall A. The heterogeneous ensembles of standard classification algorithms (HESCA): the whole is greater than the sum of its parts. arXiv preprint arXiv:1710.09220. 2017 Oct 25.
9. Leon Evangelista EDe, Descargar Sy B. An approach for improved students’ performance prediction using homogeneous and heterogeneous ensemble methods. Int J Electr Comput Eng. 2022;12(5):5226–35.
10. Ostvar N, Moghadam AME. HDEC: a heterogeneous dynamic ensemble classifier for binary datasets. Comput Intell Neurosci. 2020;2020:8826914.
11. Rokach L. Ensemble-based classifiers. Artif Intell Rev. 2010;33(1–2):1–39.
12. Romero C, Ventura S. Data mining in education. Wiley Interdiscip Rev Data Min Knowl Discov. 2013;3(1):12–27.
13. Romero C, Ventura S. Educational data mining: a survey from 1995 to 2005. Expert Syst Appl. 2007;33(1):135–46.
14. Romero C, Ventura S. Educational data mining: a review of the state of the art. IEEE Trans Syst, Man Cybern Part C: Appl Rev. 2010;40(X):601–18.
15. Tiancheng W. Online student achievement prediction model based on data envelopment analysis (DEA) for multidimensional educational internet of data mining. Int J Comput Appl. 2021;43(4):315–9.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dr. Rudi Hartono, Dr. Citra Dewi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated.
Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:
-
Share their article on personal websites, institutional repositories, or social media platforms.
-
Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.
