A Hybrid Machine Learning and Mathematical Modeling Approach for Predicting Academic Performance Using Latent Dimensions
International Journal of Innovative Science and Research Technology · 12.05.2026 · 4181
DOI: 10.38124/ijisrt/26apr1548 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 12.05.2026. Verfasst von Rajoelison Andrianarimalala Abel und 2 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben.
Abstract (Originalsprache)
Predicting academic performance is a major challenge in higher education, particularly in contexts where student monitoring systems are limited. While machine learning models have demonstrated strong predictive capabilities, their lack of interpretability limits their applicability in educational settings. This study proposes an interpretable model, the Academic Performance Index (API), based on an integrated framework combining mathematical modeling, cognitive sciences, and machine learning. Using real student data, a Random Forest model is employed to identify the most relevant variables and estimate their relative importance. These weights are then used to construct a composite index structured around four latent dimensions : cognitive, motivational, socio-economic, and environmental. The API is subsequently incorporated into a logistic regression model to estimate the probability of academic success. The results show that the proposed model achieves high predictive performance (AUC = 0.897; F1-score = 0.84), comparable to advanced approaches, while providing improved interpretability. The analysis highlights the central role of cognitive factors in academic success.
Zitieren
APA
Abel, R. A., Harinoro, R. V., & Gilbert, R. (2026). A Hybrid Machine Learning and Mathematical Modeling Approach for Predicting Academic Performance Using Latent Dimensions. International Journal of Innovative Science and Research Technology, 4181. https://doi.org/10.38124/ijisrt/26apr1548
Vancouver
Abel RA, Harinoro RV, Gilbert R. A Hybrid Machine Learning and Mathematical Modeling Approach for Predicting Academic Performance Using Latent Dimensions. International Journal of Innovative Science and Research Technology. 2026:4181. doi:10.38124/ijisrt/26apr1548
BibTeX
@article{Abel2026,
author = {Abel, Rajoelison Andrianarimalala and Harinoro, Rakotomalala Vololona and Gilbert, Rasolomampiandry},
title = {A Hybrid Machine Learning and Mathematical Modeling Approach for Predicting Academic Performance Using Latent Dimensions},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {4181},
doi = {10.38124/ijisrt/26apr1548}
}
EUVIMED