Evaluación de modelo predictivo del abandono universitario basado en clusteres de comportamiento de los/as estudiantes de primer año de Ingeniería UdeC.
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad de Concepción
Abstract
Esta memoria de título aborda el fenómeno del abandono estudiantil en la Facultad de Ingeniería de la Universidad de Concepción, centrada en los estudiantes de primer año de la cohorte 2023. El objetivo principal es analizar los factores socio académicos que influyen en la permanencia de los estudiantes, considerando tanto las diferencias de género como los diversos perfiles estudiantiles.
A través de un enfoque metodológico que incluye modelos de regresión logística y análisis de clústeres, se identificaron factores clave que afectan la retención, como el rendimiento académico medido en créditos aprobados y la posición de selección de postulación. Losresultados indican que la cantidad de créditos aprobados es un predictor significativo de la permanencia, mientras que variables como el género no muestran una influencia estadísticamente relevante.
Con base en estos hallazgos, se proponen estrategias y políticas dirigidas a mejorar la retención y apoyar de manera más efectiva a los estudiantes en riesgo de abandono, contribuyendo así a un entorno más equitativo y eficiente en la Facultad de Ingeniería de la Universidad de Concepción.
This degree project addresses the phenomenon of student dropout in the Faculty of Engineering at the University of Concepción, focusing on first-year students from the 2023 cohort. The primary objective is to analyze the socio-academic factors that influence student retention, considering both gender differences and various student profiles. Through a methodological approach that includes logistic regression models and cluster analysis, key factors affecting retention were identified, such as academic performance measured in credits earned and self-efficacy. The results indicate that the number of credits earned is a significant predictor of retention, while variables like gender do not show a statistically significant influence. Based on these findings, strategies and policies are proposed to improve retention and more effectively support students at risk of dropping out, thereby contributing to a more equitable and efficient environment within the Faculty of Engineering at the University of Concepción.
This degree project addresses the phenomenon of student dropout in the Faculty of Engineering at the University of Concepción, focusing on first-year students from the 2023 cohort. The primary objective is to analyze the socio-academic factors that influence student retention, considering both gender differences and various student profiles. Through a methodological approach that includes logistic regression models and cluster analysis, key factors affecting retention were identified, such as academic performance measured in credits earned and self-efficacy. The results indicate that the number of credits earned is a significant predictor of retention, while variables like gender do not show a statistically significant influence. Based on these findings, strategies and policies are proposed to improve retention and more effectively support students at risk of dropping out, thereby contributing to a more equitable and efficient environment within the Faculty of Engineering at the University of Concepción.
Description
Tesis presentada para optar al título de Ingeniero Civil Industrial
Keywords
Análisis de regresión logística, Estudiantes Actitudes, Estudiantes universitarios