Educational data mining: predictive analysis of academic performance of public school students in the capital of Brazil

Abstract

In this article, we present a predictive analysis of the academic performance of students in public schools of the Federal District of Brazil during the school terms of 2015 and 2016. Initially, we performed a descriptive statistical analysis to gain insight from data. Subsequently, two datasets were obtained. The first dataset contains variables obtained prior to the start of the school year, and the second included academic variables collected two months after the semester began. Classification models based on the Gradient Boosting Machine (GBM) were created to predict academic outcomes of student performance at the end of the school year for each dataset. Results showed that, though the attributes ‘grades' and ‘absences' were the most relevant for predicting the end of the year academic outcomes of student performance, the analysis of demographic attributes reveals that ‘neighborhood’, ‘school’ and ‘age’ are also potential indicators of a student's academic success or failure.