Prediction of Academic Risk among University Students Using Ensemble Algorithms and Neural Networks
International Journal of Drug Delivery Technology · 11.06.2026 · 16 (52s)
DOI: 10.25258/ijddt.16.52s.10 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 11.06.2026. Verfasst von Iván Dennys Soto Rodríguez und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Academic risk among university students can result in low performance, slow academic progress, and dropout, which is why it is important to be identified at an early stage to provide institutional intervention. In this work, ensemble learning algorithms and neural networks were compared for the prediction of academic risk among students of Universidad Nacional Agraria La Molina. The academic records of 17,233 students entering from the first semester of 2010 to the first semester of 2023 were used for the study. Academic risk was defined as two groups: students with risk and students without risk. The predictor variables were enrolled credits, approved credits, failed credits, enrolled courses, approved courses, failed courses, weighted grade, career, faculty, and performance level. The original distribution was imbalanced, and oversampling was used prior to training the model. The models evaluated were CART, Bagging, Random Forest, XGBoost, and Neural Networks. The performance was evaluated using test data and five-fold cross-validation with accuracy, F-measure, PR-AUC, recall, ROC-AUC and specificity. The findings indicated that the most significant factors that predicted academic risk were weighted grade, failed credits, and failed courses. While Bagging had a slightly higher accuracy, the Neural Network had the highest overall performance with the highest recall, specificity, PR-AUC, and ROCAUC in the test evaluation. The results showed that neural networks can be used to detect academic risk early and to assist in tutoring and academic counselling and in providing interventions for student welfare.
Zitieren
APA
Rodríguez, I. D. S., Nina, F. R. C., & Murrugarra, F. C. (2026). Prediction of Academic Risk among University Students Using Ensemble Algorithms and Neural Networks. International Journal of Drug Delivery Technology, 16(52s). https://doi.org/10.25258/ijddt.16.52s.10
Vancouver
Rodríguez IDS, Nina FRC, Murrugarra FC. Prediction of Academic Risk among University Students Using Ensemble Algorithms and Neural Networks. International Journal of Drug Delivery Technology. 2026;16(52s). doi:10.25258/ijddt.16.52s.10
BibTeX
@article{Rodrguez2026,
author = {Rodríguez, Iván Dennys Soto and Nina, Frida Rosa Coaquira and Murrugarra, Fanny Campomanes},
title = {Prediction of Academic Risk among University Students Using Ensemble Algorithms and Neural Networks},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {52s},
doi = {10.25258/ijddt.16.52s.10}
}
EUVIMED