ANÁLISE DE FATOR DE EVASÃO
O impacto do tempo na tomada decisão de alunos
Keywords:
Impact of Time, Data Analysis, Machine LearningAbstract
The article clashes different models of machine learning in the analysis of data from students who showed interest in dropping out of their graduation course due to the impact of time in making their decisions about their academic future. Firstly, a theoretical foundation on the types of machine learning will be presented and then the different models used in the research, which include the decision tree, random forest and neural network. Finally, the results will be exposed to explain the choice of method used to more effectively determine the external and internal factors that contribute to dropout as the student progresses through their semesters.This work aims to carry out an analysis of the educational data made available by data mining in the master's degree in Administration Advisory at ISCAP in Porto - PT and the internal dataset of the Universidade Jorge Amado (UNIJORGE), in order to prove he assertiveness of the course time variable in the forecast dropout rates in graduation.
References
GÉRON, Aurélien. Mãos à obra: Aprendizado de máquina com Scikit-learn & TensorFlow – conceitos, ferramentas e técnicas para a construção de sistemas inteligentes. 1. ed. Tradução de Rafael Contatori de: Hands-on machine learning with Scikit-learn & TensorFlow. Rio de Janeiro: Atlas Books, 2019. ISBN: 978-85-508-0381-4.
KUMAR, V. Uday; KRISHNA, Azmira. Advanced prediction of performance of a student in an university using machine learning techniques. In: INTERNATIONAL CONFERENCE ON ELECTRONICS AND SUSTAINABLE COMMUNICATION SYSTEMS (ICESC). Agosto de 2020.Anais [...]. [S.l], agosto de 2020. DOI. 10.1109/ICESC48915.2020.9155557.
MARR, B. Big Data: Using SMART big data, analytics and metrics to make better decisions and improve performance. [S.l.]: John Wiley & Sons, 2015.
NETO, Cesare Di Girolamo. Potencial de técnicas de mineração de dados para o mapeamento de áreas cafeeiras. INPE, São José dos Campos, 2014.
SILVA, Fernanda Cristina da; CABRAL, Thiago Luiz de Oliveira; PACHECO, Andressa Sasaki Vasques. Evasão ou permanência? Modelos preditivos para a gestão do ensino superior. AAPE – Arquivos Analíticos de Políticas Educativas, [s.l.], v. 28, n. 149, 2020.
SULTANA, Sara; KHAN, Sharifullah; ABBAS, Muhammad A. Predicting performance of electrical engineering students using cognitive and non-cognitive features for identification of potential dropouts. International Journal of Electrical Engineering Education, [s.l.], v. 54, p. 105-118, 2017. DOI: 10.1177/0020720916688484.
SILVA, Andréa Ferreira da; ALMEIDA, Aléssio Tony Cavalcanti de; RAMALHO, Hilton Martins de Brito. Predição do risco de reprovação no ensino superior usando algoritmos de machine learning. Teoria e Prática em Administração, [s.l.], v. 10, n. 2, p. 58-80, jul-dez., 2020. DOI. 10.21714/2238-104X2020v10i2-51124.
WAGNER BANDEIRA ANDRIOLA; CRISTIANY GOMES ANDRIOLA; CRISTIANE PASCOAL MOURA. Opiniões de docentes e de coordenadores acerca do fenômeno da evasão discente dos cursos de graduação da Universidade Federal do Ceará. Ensaio de políticas públicas educacionais, v. 14, n. 52, setembro de 2006.
