Advisor(s)
Abstract(s)
Este estudo propõe dois modelos preditivos de classificação que permitem
identificar, logo no final do 1º e do 2º semestres escolares, os estudantes de licenciatura
de uma instituição de ensino superior mais propensos ao abandono académico. A
metodologia proposta, que combina 3 algoritmos populares de data mining, como são
as random forest, as máquinas de vetores de suporte e as redes neuronais artificiais,
para além de contribuir para a assertividade da previsão, permite identificar por
ordem de relevância os principais fatores que prenunciam o abandono académico. Os
resultados empíricos demonstram ser possível reduzir para cerca de 1/4 as 4 dezenas de
potenciais preditores do abandono, e mostram serem essencialmente dois, do contexto
curricular do estudante, a explicarem essa propensão. Esse conhecimento revela-se
de importância primordial para que os agentes de gestão possam adotar as medidas e
decisões estratégicas mais propícias à diminuição dos índices de evasão discente.
This study proposes two predictive models of classification that allow to identify, at the end of the 1st and 2nd semesters, the undergraduate students of a higher education institution more prone to academic dropout. The proposed methodology, which combines 3 popular data mining algorithms, such as random forest, support vector machines and artificial neural networks, in addition to contributing to predictive performance, allows to identify the main factors behind academic dropout. The empirical results show that it is possible to reduce to about 1/4 the 4 tens potential predictors of dropout, and show that there are essentially two predictors, concerning student’s curriculum context, that explain this propensity. This knowledge is useful for decision-makers to adopt the most appropriate strategic measures and decisions in order to reduce student dropout rates.
This study proposes two predictive models of classification that allow to identify, at the end of the 1st and 2nd semesters, the undergraduate students of a higher education institution more prone to academic dropout. The proposed methodology, which combines 3 popular data mining algorithms, such as random forest, support vector machines and artificial neural networks, in addition to contributing to predictive performance, allows to identify the main factors behind academic dropout. The empirical results show that it is possible to reduce to about 1/4 the 4 tens potential predictors of dropout, and show that there are essentially two predictors, concerning student’s curriculum context, that explain this propensity. This knowledge is useful for decision-makers to adopt the most appropriate strategic measures and decisions in order to reduce student dropout rates.
Description
Keywords
Artificial neural networks Educational data mining Prediction academic dropout Random forest Support vector machines
Citation
Martins, Maria Prudência; Migueis, Vera L.; Fonseca, D. S.B.; Gouveia, Paulo D.F. (2020). Previsão do abandono académico numa instituição de ensino superior com recurso a data mining = Prediction of academic dropout in a higher education institution using data mining. RISTI - Revista Iberica de Sistemas e Tecnologias de Informação. ISSN 1646-9895. p. 188-203