Prognóstico da Evasão Escolar em Instituição de Educação Profissional e Tecnológica por meio da Inteligência Artificial

Authors

  • Carlos Vital Giordano Centro Paula Souza, São Paulo, Brasil.
  • Raphael Antonio de Souza Centro Paula Souza, São Paulo, Brasil

DOI:

https://doi.org/10.25755/int.29456

Abstract

School dropout is a worrisome problem for educational institutions, society, educational policy makers, and students. The early identification of students with high dropout probability is essential in the establishment of actions to prevent the disorder. The research aims to verify the option of using Machine Learning (ML) algorithm to identify students with higher dropout risk. Using an Auto Machine Learning (AutoML) tool, the data of 1,222 students from an IEPT technical course was analyzed. After pre-processing the data, the purged data was submitted to the AutoML tool, which generated an algorithm model with accuracy higher than 90.0% when identifying students with the possibility of dropping out. The study results demonstrate the favorable perspective in the use of AM in educational data.

Author Biographies

Carlos Vital Giordano, Centro Paula Souza, São Paulo, Brasil.

Professor at the Professional Master's Program in Management and Development of Professional Education at Centro Paula Souza, São Paulo, Brazil.

Raphael Antonio de Souza, Centro Paula Souza, São Paulo, Brasil

Mestrando do programa de mestrado profissional em gestão e desenvolvimento da educação profissional do CEETEPS.

Downloads

Published

2023-08-28

How to Cite

Giordano, C. V., & Souza, R. A. de . (2023). Prognóstico da Evasão Escolar em Instituição de Educação Profissional e Tecnológica por meio da Inteligência Artificial. Interacções, 19(66), 1–20. https://doi.org/10.25755/int.29456

Issue

Vol. 19 No. 66 (2023): Número Especial (2) - Recomposição das Aprendizagens & Renovação de Práticas Metodológicas e de Gestão

Section

Number 25 - Special Number - Adolescence, Gender and Violences

License

Copyright (c) 2023 Interacções

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a  CC BY-NC-SA 4.0 license that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.