Predictive model based on machine learning for the early identification of student dropout in a public university

Aparicio-Montenegro P.; Silva Milciades Roberto E.; Sotero Armando H.; Garcia-Alvarez M.Y.; De La Cruz Garcia A. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2026) · DOI: 10.18687/laccei2026.1.1.721

Resumen

Student dropout represents a significant problem in public universities, with academic, economic, and social repercussions. This study aims to develop a predictive model based on machine learning techniques for the early identification of students at risk of dropping out. This will allow for the implementation of measures capable of reducing dropout rates through intervention strategies such as personalized tutoring and socioeconomic support. The data used includes academic, socioeconomic, and behavioral data corresponding to the periods 2015-2024. The methodology applied is quantitative and predictive, using algorithms linked to supervised learning techniques such as Logistic Regression, Decision Trees, Random Forest, and AdaBoost. The data were preprocessed through cleaning, Z-score normalization, and balancing with SMOTE. They were then divided into training (70%), validation (15%), and test (15%) sets, and k-fold cross-validation (k = 5) was applied. The performance of the models was evaluated using accuracy, precision, recall, F1-score, and area under the ROC curve. The results indicated that the AdaBoost model performed best, achieving an accuracy of approximately 89% and an AUC of 0.957, surpassing Random Forest (AUC = 0.902) and Logistic Regression (AUC = 0.948). Therefore, it is concluded that the proposed model could be considered a suitable tool for the early detection of students at risk of dropping out.

Instituciones: Universidad Tecnológica del Perú; Universidad Nacional Federico Villarreal