MAGRA
The Undergraduate Analysis Model (MAGRA) enables the prediction of dropout rates in face-to-face undergraduate courses.
Brasília, January 2023.
The Undergraduate Analysis Model (MAGRA) is an innovation designed to enhance understanding of the risk of student dropout at the University of Brasília (UnB). This pioneering tool combines indicators extracted from UnB’s academic systems with the power of machine learning, offering accurate predictions and valuable insights.
The development of MAGRA stemmed from a meticulous literature review, which laid the groundwork for the careful selection of variables and the application of the most effective analytical methods. This comprehensive process ranges from data selection and preparation to the execution of an ETL (Extract, Transform, Load) procedure, culminating in the use of machine learning algorithms to draw meaningful conclusions.
Conceived within the context of a master’s thesis, MAGRA not only identifies students at potential risk of dropout; it also engages in a dialogue with existing research in the field, enriching academic management with a comparative analysis and a detailed narrative on the effectiveness of its predictions.
Author: Edmilson Cosme da Silva
Advisor: Prof. Sergio Freitas
Latest news about this product
INPI grants software registration for Euploidy Prediction with Machine Learning
The software for non-invasive prediction of euploidy in human embryos received a computer program registration certificate granted by INPI, under process BR512026003650-0.
INPI grants software registration for FCTE Student Support
The FCTE Student Support software received a computer program registration certificate granted by INPI, under process BR512026003515-5.
CEDIS presents Evidentia Review for systematic literature reviews
Evidentia Review, software developed by CEDIS, helps research teams plan, conduct, and report systematic literature reviews with audit trails and reproducible reports.