Volume 4 • Issue 1 • PP: 07–15 • 2025
Early Detection of Student Dropout Risk in Higher Education through Optimized Machine Learning
Open Access & Copyright
© 2025 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
View PDF Abstract
Student retention in higher education institutions is a critical problem that causes academic and financial challenges to individual students, schools, and entire countries. The present study compares five machine-learning classifiers—Linear Discriminant Analysis (LDA), K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GBM)—using data for 4,424 students from the Realinho et al. (2022) dataset. The dataset contains demographic, socioeconomic, macroeconomic, and academic-performance information from a Portuguese higher-education institution. Mutual-information feature selection reduces the 22-dimensional feature space to the 12 features with the highest discriminative power. Five-fold stratified cross-validation shows that the SVM with a radial-basis-function kernel achieves the best overall performance, with 97.1% accuracy and an F1-score of 0.954; all five models achieve an AUC greater than 0.981. The importance analysis reveals that four measures of academic success from the first two semesters account for 87.6% of the Random Forest feature importance, driven by the number of curricular units passed during the second semester (importance = 0.335). Socioeconomic, demographic, and macroeconomic features together contribute less than 13%. These findings provide empirical evidence about student-retention risk factors and inform the design of higher-education early-warning systems.
Keywords
References
[1] V. Realinho, J. Machado, L. Baptista, and M. V. Mar-tins, “Predicting student dropout and academic success,” Data, vol. 7, no. 11, p. 146, 2022.
[2] A. González-Nucamendi, J. Noguez, L. Neri, V. Robledo-Rella, and R. M. G. García-Castelán, “Predictive analytics study to determine undergraduate students at risk of dropout,” Frontiers in Education, vol. 8, p. 1244686, 2023.
[3] M. Hlosta, C. Herodotou, T. Papathoma, A. Gillespie, and P. Bergamin, “Predictive learning analytics in online education: A deeper understanding through explaining algorithmic errors,” Computers and Education: Artifi-cial Intelligence, vol. 3, p. 100108, 2022.
[4] R. S. Baker and A. Hawn, “Algorithmic bias in educa-tion,” International Journal of Artificial Intelligence in Education, vol. 32, no. 4, pp. 1052–1092, 2022.
[5] B. Alnasyan, M. Basheri, and M. Alassafi, “The power of deep learning techniques for predicting student per-formance in virtual learning environments: A systematic literature review,” Computers and Education: Artificial Intelligence, vol. 6, p. 100231, 2024.
[6] R. Mahafdah, S. Bouallegue, and R. Bouallegue, “En-hancing e-learning through ai: Advanced techniques for optimizing student performance,” PeerJ Computer Science, vol. 10, p. e2576, 2024.
[7] L. Jin, Y. Wang, H. Song, and H.-J. So, “Predictive mod-elling with the open university learning analytics dataset (oulad): A systematic literature review,” In Artificial Intelligence in Education: Posters and Late Breaking Results, Workshops and Tutorials, Communications in Computer and Information Science, vol. 2150, Springer, pp. 477–484, 2024.
[8] M.-R. Borna, H. Saadat, A. T. Hojjati, and E. Akbari, “Analyzing click data with ai: Implications for student performance prediction and learning assessment,” Fron-tiers in Education, vol. 9, p. 1421479, 2024.
[9] H. Althibyani, “Predicting student success in moocs: A comprehensive analysis using machine learning models,” PeerJ Computer Science, vol. 10, p. e2221, 2024.
[10] J. H. Guanin-Fajardo, J. Guaña-Moya, and J. Casillas, “Predicting academic success of college students using machine learning techniques,” Data, vol. 9, no. 4, p. 60, 2024.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.