A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://doi.org/10.29352/mill0223.31378 |
Resumo: | Introduction: University dropout is now considered a complex phenomenon that goes beyond the number of students not enrolled and that is continuously growing, especially in the first years of study. Objective: In the present study, a prediction model combining Survival Analysis, Decision Trees, and Random Forest, under the Machine Learning philosophy, is proposed for the early diagnosis of possible factors causing dropout in university students. Methods: The proposal consists of 3 phases: the Survival Analysis that allows estimating the probability of permanence of the student (survival). Phase 2 starts from the probability value obtained in the previous phase and uses it as a response variable in the modeling process based on Decision Trees to establish survival patterns around the variables considered. Finally, in phase 3, the critical variables in the model are identified using the Random Forest. Results: The proposed methodology allowed the design of a prediction model to identify the main segmentation variables in behavior patterns of possible cases of academic dropout. Conclusion: Even though the proposal was developed considering a particular case of a Chilean university, the efficient combination of metaheuristics allows the extrapolation of the methodology to any context and academic reality. However, the conditions and needs of each institution must be considered. |
id |
RCAP_4829f5944384d0439210d3a6cecf1d6a |
---|---|
oai_identifier_str |
oai:ojs.revistas.rcaap.pt:article/31378 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case studyUna propuesta metodológica para abordar el fenómeno de la deserción académica a partir de un modelo de predicción inteligente: un caso de estudioUma proposta metodológica para abordar o fenômeno da deserção acadêmica a partir de um modelo de predição inteligente: um estudo de casoEducation and Social Development SciencesIntroduction: University dropout is now considered a complex phenomenon that goes beyond the number of students not enrolled and that is continuously growing, especially in the first years of study. Objective: In the present study, a prediction model combining Survival Analysis, Decision Trees, and Random Forest, under the Machine Learning philosophy, is proposed for the early diagnosis of possible factors causing dropout in university students. Methods: The proposal consists of 3 phases: the Survival Analysis that allows estimating the probability of permanence of the student (survival). Phase 2 starts from the probability value obtained in the previous phase and uses it as a response variable in the modeling process based on Decision Trees to establish survival patterns around the variables considered. Finally, in phase 3, the critical variables in the model are identified using the Random Forest. Results: The proposed methodology allowed the design of a prediction model to identify the main segmentation variables in behavior patterns of possible cases of academic dropout. Conclusion: Even though the proposal was developed considering a particular case of a Chilean university, the efficient combination of metaheuristics allows the extrapolation of the methodology to any context and academic reality. However, the conditions and needs of each institution must be considered.Introducción: La deserción universitaria se considera actualmente como un fenómeno complejo que va más alla del número de estudiantes no matriculados, y que viene en continuo crecimiento sobre todo en los primeros años de estudio. Objetivo: En el presente estudio se propone un modelo de predicción que combina el Análisis de Supervivencia, Árboles de Decisión y Random Forest, bajo la filosofía de Machine Learning, para el diagnóstico temprano de los posibles factores de la deserción en estudiantes universitarios. Métodos: La propuesta consta de 3 fases: el Análisis de Supervivencia que permite estimar la probabilidad de permanencia del alumno (supervivencia). La fase 2 parte del valor de probabilidad obtenido en la fase anterior y lo utiliza como variable respuesta en el proceso de modelado basado en los árboles de decisión para establecer patrones de supervivencia en torno a las variables consideradas. Finalmente, en la fase 3 se identifican las variables más importantes en el modelo, utilizando Random Forest. Resultados: La metodología propuesta permitió diseñar un modelo de predicción, que identifica las principales variables de segmentación en patrones de comportamiento de posibles casos de deserción académica. Conclusión: Si bien la propuesta fue desarrollada considerando un caso particular de una universidad chilena, la eficiente combinación de la metaheurística permite la extrapolación de la metodología a cualquier contexto y realidad académica. Sin embargo, se deben considerar las condiciones y necesidades de cada institución.Introdução: A deserção universitária é atualmente considerada um fenômeno complexo que vai além do número de estudantes não matriculados, e que vem em contínuo crescimento sobretudo nos primeiros anos de estudo. Objetivo: No presente estudo, é proposto um modelo de predição que combina Análise de Sobrevivência, Árvores de Decisão e Random Forest, sob a filosofia de Machine Learning, para o diagnóstico precoce dos possíveis fatores de deserção em estudantes universitários. Métodos: A proposta consiste em 3 fases: a Análise de Sobrevivência que permite estimar a probabilidade de permanência do aluno (sobrevivência). A fase 2 parte do valor de probabilidade obtido na fase anterior e o utiliza como variável resposta no processo de modelagem baseado em árvores de decisão para estabelecer padrões de sobrevivência em torno das variáveis consideradas. Finalmente, na fase 3, as variáveis críticas do modelo são identificadas usando Random Forest. Resultados: A metodologia proposta permitiu desenhar um modelo de previsão, que identifica as principais variáveis de segmentação em padrões de comportamento de possíveis casos de deserção acadêmica. Conclusão: Embora a proposta tenha sido desenvolvida a partir de um caso particular de uma universidade chilena, a combinação eficiente da meta-heurística permite a extrapolação da metodologia para qualquer contexto e realidade acadêmica. No entanto, devem ser consideradas as condições e necessidades de cada instituição.Polytechnic Institute of Viseu (IPV)2023-11-22info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttps://doi.org/10.29352/mill0223.31378eng1647-662X0873-3015Villa-Murillo, AdrianaCosta, LuísVásquez, Carlosinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-14T17:01:52Zoai:ojs.revistas.rcaap.pt:article/31378Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:19:33.437134Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study Una propuesta metodológica para abordar el fenómeno de la deserción académica a partir de un modelo de predicción inteligente: un caso de estudio Uma proposta metodológica para abordar o fenômeno da deserção acadêmica a partir de um modelo de predição inteligente: um estudo de caso |
title |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
spellingShingle |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study Villa-Murillo, Adriana Education and Social Development Sciences |
title_short |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
title_full |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
title_fullStr |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
title_full_unstemmed |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
title_sort |
A methodological proposal to address the academic dropout phenomenon based on an intelligent prediction model: a case study |
author |
Villa-Murillo, Adriana |
author_facet |
Villa-Murillo, Adriana Costa, Luís Vásquez, Carlos |
author_role |
author |
author2 |
Costa, Luís Vásquez, Carlos |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Villa-Murillo, Adriana Costa, Luís Vásquez, Carlos |
dc.subject.por.fl_str_mv |
Education and Social Development Sciences |
topic |
Education and Social Development Sciences |
description |
Introduction: University dropout is now considered a complex phenomenon that goes beyond the number of students not enrolled and that is continuously growing, especially in the first years of study. Objective: In the present study, a prediction model combining Survival Analysis, Decision Trees, and Random Forest, under the Machine Learning philosophy, is proposed for the early diagnosis of possible factors causing dropout in university students. Methods: The proposal consists of 3 phases: the Survival Analysis that allows estimating the probability of permanence of the student (survival). Phase 2 starts from the probability value obtained in the previous phase and uses it as a response variable in the modeling process based on Decision Trees to establish survival patterns around the variables considered. Finally, in phase 3, the critical variables in the model are identified using the Random Forest. Results: The proposed methodology allowed the design of a prediction model to identify the main segmentation variables in behavior patterns of possible cases of academic dropout. Conclusion: Even though the proposal was developed considering a particular case of a Chilean university, the efficient combination of metaheuristics allows the extrapolation of the methodology to any context and academic reality. However, the conditions and needs of each institution must be considered. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-11-22 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://doi.org/10.29352/mill0223.31378 |
url |
https://doi.org/10.29352/mill0223.31378 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1647-662X 0873-3015 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Polytechnic Institute of Viseu (IPV) |
publisher.none.fl_str_mv |
Polytechnic Institute of Viseu (IPV) |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799135493878710272 |