Predicting undergraduate academic performance in a leading Peruvian university: A machine learning approach

• Autores: Salas, Fabio, Caldas, Josué
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Pontificia Universidad Católica del Perú
• Repositorio: Revistas - Pontificia Universidad Católica del Perú
• Lenguaje: inglés
• OAI Identifier: oai:revistaspuc:article/28596
• Enlace del recurso: http://revistas.pucp.edu.pe/index.php/educacion/article/view/28596
• Nivel de acceso: acceso abierto
• Materia: Academic performance; Machine Learning; Higher Education; Peru; Rendimiento Académico; Educación Superior; Perú; Desempenho Acadêmico; Aprendizado de Máquina; Ensino Superior

Despite improved higher education accessibility in low and middle-income countries (LMICs), challenges persist in student drop-out, especially for socio-economically disadvantaged students. While machine learning models have enhanced our understanding of this challenge by predicting academic performance, many studies overlook LMIC-specific institutional factors or focus on specific courses, limiting their generalizability and policy uses. To address these issues, the authors compiled a comprehensive database using administrative and census data to predict undergraduate academic performance at the Pontifical Catholic University of Peru (PUCP). The study found that the most effective models were tree-based ensembles, particularly Random Forest, with key predictors including prior secondary school performance and university admission test scores. They present a high-performing model using only ten features that can predict future academic performance and potentially aid in reducing student drop-out at PUCP.