Modelo predictivo para la prevención de la deserción académica en estudiantes de un instituto tecnológico de Puno, 2025

Fuentes: histórico de OJS (PKP, por objeto) + tracker en la revista + 2 vista(s) en este índice. Citas: se consultan en Crossref para publicaciones con DOI.

Resumen

The objective of this study was to develop a predictive model to prevent academic dropout among students at a technological institute in Puno during the year 2025. The problem addressed lies in the high school dropout rates in rural regions of Peru, influenced by socioeconomic, academic, and personal factors. The research was basic-applied, with a quantitative approach, descriptive and explanatory design, and cross-sectional scope. The population consisted of all students enrolled in the institute in 2025, while the sample consisted of 300 students selected through stratified sampling. The quantitative results show that variables such as poor performance in the first semester, precarious socioeconomic conditions, advanced age at entry, and gender significantly influence the risk of dropping out. The predictive model, based on machine learning techniques such as logistic regression and decision trees, achieved high levels of precision and recall. It is concluded that early identification of at-risk students through predictive models allows for the design of effective intervention strategies. Its institutional implementation is recommended, along with personalized academic, financial, and emotional support measures, which could significantly improve student retention in similar contexts.

Lecturas por mes y tendencia

Barras: vistas del resumen y lecturas de archivos (tracker + índice). Línea punteada: tendencia lineal y predicción de 3 meses (estimación estadística, no un dato).

Palabras clave

Academic dropoutpredictive modelhigher educationmachine learningAbandono académicomodelo predictivoeducación superioraprendizaje automático