Logo PUC-Rio Logo Maxwell
ETDs @PUC-Rio
Estatística
Título: THE APPLICATION OF MACHINE LEARNING FRAMEWORK TO IDENTIFY STUDENTS AT RISK OF DEFAULT IN A HIGHER EDUCATION INSTITUTION
Autor: GIOVANNA NISKIER SAADIA
Colaborador(es): JORGE BRANTES FERREIRA - Orientador
Catalogação: 26/MAI/2020 Língua(s): PORTUGUESE - BRAZIL
Tipo: TEXT Subtipo: THESIS
Notas: [pt] Todos os dados constantes dos documentos são de inteira responsabilidade de seus autores. Os dados utilizados nas descrições dos documentos estão em conformidade com os sistemas da administração da PUC-Rio.
[en] All data contained in the documents are the sole responsibility of the authors. The data used in the descriptions of the documents are in conformity with the systems of the administration of PUC-Rio.
Referência(s): [pt] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/ETDs/consultas/conteudo.php?strSecao=resultado&nrSeq=48281&idi=1
[en] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/ETDs/consultas/conteudo.php?strSecao=resultado&nrSeq=48281&idi=2
DOI: https://doi.org/10.17771/PUCRio.acad.48281
Resumo:
As impressive as the growth rate in the number of enrollments in private higher education institutions in recent years is the increase in the related default rate, driven by the deepening economic crisis in Brazil and by the reduction of the number of vacancies offered by the FIES. Default presents itself as a challenge to the financial management of educational institutions, since it impacts their operational costs and ends up being passed on to students in the form of an increase in tuition. In addition, student dropout is also one of the main consequences of default, since students with economic difficulties end up abandoning their courses. Most higher education institutions do not use any type of credit scoring analysis to predict the risk of their students becoming defaulters, failing to understand which factors cause it, and, therefore, refraining from planning preventive actions. Therefore, this study presents a quantitative methodology to predict the default risk of active students. Models generated by machine learning algorithms were analyzed based on a historical database of students who were in or not in default. The results showed a relationship between default and economic, academic and social characteristics of students. Thus, by employing models such as the ones proposed, higher education institutions should be able to identify those students who are at higher risk of defaulting and take specific preventive actions to prevent such an outcome.
Descrição: Arquivo:   
COMPLETE PDF