Predictive Model to Identify College Students with High Dropout Rates

Predictive Model to Identify College Students with High Dropout Rates

Decreasing student attrition rates is one of the main objectives of most higher education institutions. However, to achieve this goal, universities need to accurately identify and focus their efforts on students most likely to quit their studies before they graduate. This has given rise to a need to...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hoyos Osorio, Jhoan Keider, Daza Santacoloma, Genaro
Formato: Online
Lenguaje:eng
spa
Publicado: Universidad Autónoma de Baja California. Instituto de Investigación y Desarrollo Educativo 2023
Acceso en línea:https://redie.uabc.mx/redie/article/view/5398
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id redie-article-5398
record_format ojs
spelling redie-article-53982023-12-23T01:34:14Z Predictive Model to Identify College Students with High Dropout Rates Modelo predictivo para identificar estudiantes universitarios con alto grado de deserción Modelo preditivo para identificar estudantes universitários com alto risco de evasão Hoyos Osorio, Jhoan Keider Daza Santacoloma, Genaro dropping out college students forecasting regression analysis deserción escolar estudiante universitario previsión análisis de regresión evasão escolar estudante universitário previsão análise de regressão Decreasing student attrition rates is one of the main objectives of most higher education institutions. However, to achieve this goal, universities need to accurately identify and focus their efforts on students most likely to quit their studies before they graduate. This has given rise to a need to implement forecasting models to predict which students will eventually drop out. In this paper, we present an early warning system to automatically identify first-semester students at high risk of dropping out. The system is based on a machine learning model trained from historical data on first-semester students. The results show that the system can predict “at-risk” students with a sensitivity of 61.97%, which allows early intervention for those students, thereby reducing the student attrition rate. Disminuir la tasa de deserción estudiantil es uno de los principales objetivos de las instituciones de educación superior; para lograrlo, las universidades deben identificar con precisión a los estudiantes con mayor riesgo de abandonar los estudios antes de graduarse y centrar sus esfuerzos en ellos. De ahí surge la necesidad de implementar modelos predictivos capaces de identificar a los estudiantes que finalmente desertarán. En este trabajo se presenta un sistema de alerta temprana para identificar a los estudiantes de primer semestre con alto riesgo de deserción; el sistema se basa en un modelo de aprendizaje automático entrenado a partir de datos históricos de estudiantes de primer semestre. Los resultados muestran que el sistema puede identificar a los estudiantes “en riesgo” con una sensibilidad del 61.97%, lo que permite ofrecerles atención temprana y reducir la tasa de abandono. Reduzir a taxa de evasão estudantil é um dos principais objetivos das instituições de ensino superior; para conseguir isso, as universidades devem identificar com precisão os alunos com maior risco de abandonar os estudos antes da conclusão do curso e concentrar seus esforços neles. Daí surge a necessidade de implementar modelos preditivos capazes de identificar os alunos que acabarão por desistir. Este artigo apresenta um sistema de alerta precoce para identificar alunos do primeiro semestre com alto risco de evasão; o sistema é baseado em um modelo de aprendizagem automático treinado a partir de dados históricos de alunos do primeiro semestre. Os resultados mostram que o sistema pode identificar os alunos “em risco” com uma sensibilidade de 61.97%, o que possibilita oferecer-lhes atendimento precoce e reduzir o índice de evasão. Universidad Autónoma de Baja California. Instituto de Investigación y Desarrollo Educativo 2023-05-03 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Text Texto text/html application/pdf text/xml application/epub+zip audio/mpeg https://redie.uabc.mx/redie/article/view/5398 10.24320/redie.2023.25.e13.5398 Revista Electrónica de Investigación Educativa; Vol. 25 (2023); 1-10 Revista Electrónica de Investigación Educativa; Vol. 25 (2023); 1-10 1607-4041 eng spa https://redie.uabc.mx/redie/article/view/5398/2399 https://redie.uabc.mx/redie/article/view/5398/2400 https://redie.uabc.mx/redie/article/view/5398/2417 https://redie.uabc.mx/redie/article/view/5398/2404 https://redie.uabc.mx/redie/article/view/5398/2434 Derechos de autor 2023 Jhoan Keider Hoyos Osorio, Genaro Daza Santacoloma https://creativecommons.org/licenses/by-nc/4.0
institution REDIE
collection OJS
language eng
spa
format Online
author Hoyos Osorio, Jhoan Keider
Daza Santacoloma, Genaro
spellingShingle Hoyos Osorio, Jhoan Keider
Daza Santacoloma, Genaro
Predictive Model to Identify College Students with High Dropout Rates
author_facet Hoyos Osorio, Jhoan Keider
Daza Santacoloma, Genaro
author_sort Hoyos Osorio, Jhoan Keider
title Predictive Model to Identify College Students with High Dropout Rates
title_short Predictive Model to Identify College Students with High Dropout Rates
title_full Predictive Model to Identify College Students with High Dropout Rates
title_fullStr Predictive Model to Identify College Students with High Dropout Rates
title_full_unstemmed Predictive Model to Identify College Students with High Dropout Rates
title_sort predictive model to identify college students with high dropout rates
description Decreasing student attrition rates is one of the main objectives of most higher education institutions. However, to achieve this goal, universities need to accurately identify and focus their efforts on students most likely to quit their studies before they graduate. This has given rise to a need to implement forecasting models to predict which students will eventually drop out. In this paper, we present an early warning system to automatically identify first-semester students at high risk of dropping out. The system is based on a machine learning model trained from historical data on first-semester students. The results show that the system can predict “at-risk” students with a sensitivity of 61.97%, which allows early intervention for those students, thereby reducing the student attrition rate.
publisher Universidad Autónoma de Baja California. Instituto de Investigación y Desarrollo Educativo
publishDate 2023
url https://redie.uabc.mx/redie/article/view/5398
_version_ 1792095027420200960

Ejemplares similares