A Machine Learning-Based Computational System Proposal Aiming at Higher Education Dropout Prediction

  •  Maria do Carmo Nicoletti    
  •  Osvaldo Luiz de Oliveira    


In the literature related to higher education, the concept of dropout has been approached from several perspectives and, over the years, its definition has been influenced by the use of diversified semantic interpretations. In a general higher education environment dropout can be broadly characterized as the act of a student engaged in a course leaving the educational institution without finishing the course. This paper describes the proposal of the architecture of a computational system, PDE (Predicting Dropout Events), based on machine learning (ML) algorithms and specifically designed for predicting dropout events in a higher level educational environment. PDE’s main subsystem implements a group of instance-based learning (IBL) algorithms which, taking into account a particular university-course environment, and based on log files containing descriptions of previous dropouts events, is capable to predict when a student already engaged in the course, is prone to dropout, so preventive measures could be quickly implemented.

This work is licensed under a Creative Commons Attribution 4.0 License.
  • ISSN(Print): 1925-4741
  • ISSN(Online): 1925-475X
  • Started: 2011
  • Frequency: quarterly

Journal Metrics

h-index (December 2020): 38

i10-index (December 2020): 169

h5-index (December 2020): 18

h5-median(December 2020): 32

(The data was calculated based on Google Scholar Citations. Click Here to Learn More. )