Identificação, Análise e Apoio à Tomada de Decisão sobre Evasão Escolar no Contexto de um Curso de Engenharia de Computação

Abstract

The school dropout rate in the IT field in Brazil was around 60.2%in 2017, according to data released by the Ministry of Education’sHigher Education Census. Considering this fact, this paper aimsto establish patterns regarding students who have abandoned theComputer Engineering course at a federal institution in Brazil, usinga predictive model. An intelligent system capable of predictingif a student will drop out or not based on his academic historywas proposed and implemented. The methodology for the systemdevelopment included four distinct phases. In the first phase, a dataextraction algorithm from academic histories was developed. Thesecond phase encompassed correlation analyses and the generationof a decision tree to identify dropout indicators, using data from 180students. Despite data limitations, the model achieved 78% accuracy.In the third and fourth phase an Application Programming Interface(API) and a system dashboard were implemented to achieve theproposed goal.