Enfoque de análisis de datos visual - predictivo para el desempeño académico de los estudiantes de una universidad peruana

Abstract

The academic success of university students is a result that depends in a multi-factorial way on the aspects related to the student and the career itself. In this work, we carry out a visual analysis of the data to obtain relevant information regarding the academic performance of students from a Peruvian university. This study was complemented with the construction of machine learning models to provide a predictive model of the students’ academic success. In specific, the XGBoost Machine Learning method achieved a performance of up to 91.5% of Accuracy. In this sense, this study offers a novel visual-predictive data analysis approach as a valuable tool for developing and targeting policies to support students with lower academic performance or to stimulate advanced students. The results obtained allow us to identify the relevant variables associated with the students’ academic performances. Moreover, we were able to give some insight into the academic situation of the different careers of the University.