Analysis of the academic performance of Systems Engineering students, desertion possibilities and proposals for retention

Abstract

Problems of academic lag and desertion affect educational institutions, students, and their families. This study analyzes the academic performance of the 2011-2016 cohorts of the Professional School of Systems Engineering at a public university, using data from 976 students, including admission scores, grades, and personal information. Data mining techniques such as neural networks and decision trees are applied to identify patterns. The most influential variables are the exogenous performance index and the ratio of approved credits to expected credits. Strategies are proposed to reduce desertion and improve academic performance.