Early Warning System for Detecting Student Dropouts Using the Random Forest Algorithm at SMKS Alhuda
Journal of Artificial Intelligence and Engineering Applications (JAIEA) · 15.06.2026 · 5 (3) · 4239-4244
DOI: 10.59934/jaiea.v5i3.2385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Artificial Intelligence and Engineering Applications (JAIEA), online erschienen am 15.06.2026. Verfasst von Muhammad Khoerulrijjal Salsabila Januarta und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
The dropout rate in vocational high schools poses a serious challenge that requires an objective early-detection system. This study aims to optimize a model for predicting student dropout risk by utilizing a supervised learning approach. The study uses multivariate data covering student demographic attributes, academic achievement, behavior, and financial history. The Random Forest algorithm was implemented to classify student risk levels into Safe, Caution, and Danger categories to support preventive decision-making. Model performance testing using a confusion matrix showed an accuracy rate of 99%, with a recall of 100% in the High-Risk category, demonstrating the algorithm’s effectiveness in accurately identifying high-risk students. These findings contribute to the development of more precise early detection methods in educational settings.
Zitieren
APA
Januarta, M. K. S., & Setyoningrum, N. G. (2026). Early Warning System for Detecting Student Dropouts Using the Random Forest Algorithm at SMKS Alhuda. Journal of Artificial Intelligence and Engineering Applications (JAIEA), 5(3), 4239-4244. https://doi.org/10.59934/jaiea.v5i3.2385
Vancouver
Januarta MKS, Setyoningrum NG. Early Warning System for Detecting Student Dropouts Using the Random Forest Algorithm at SMKS Alhuda. Journal of Artificial Intelligence and Engineering Applications (JAIEA). 2026;5(3):4239-4244. doi:10.59934/jaiea.v5i3.2385
BibTeX
@article{Januarta2026,
author = {Januarta, Muhammad Khoerulrijjal Salsabila and Setyoningrum, Nuk Ghurroh},
title = {Early Warning System for Detecting Student Dropouts Using the Random Forest Algorithm at SMKS Alhuda},
journal = {Journal of Artificial Intelligence and Engineering Applications (JAIEA)},
year = {2026},
volume = {5},
number = {3},
pages = {4239--4244},
doi = {10.59934/jaiea.v5i3.2385}
}
EUVIMED