Perspectives to Predict Dropout in University Students with Machine Learning

Martin Solis, Tania Moreira, Roberto Gonzalez, Tatiana Fernandez, Maria Hernandez

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

47 Citas (Scopus)

Resumen

This study analyzes the performance of four machine learning algorithms with different perspectives for defining data files, in the prediction of university student desertion. The algorithms used were: Random Forest, Neural Networks, Support Vector Machines and Logistic Regression. It was found that the Random Forest algorithm with 10 variables randomly sampled as candidates in each division, was the best for predicting dropouts and that the ideal perspective for training the algorithm is to use information on all semesters that students take within a given period of time, using a classification variable that defines the non-dropout as the graduated student. In a first validation sample, this approach correctly predicted 91% of dropouts, with a sensitivity of 87%.

Idioma originalInglés
Título de la publicación alojada2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión impresa)9781538675069
DOI
EstadoPublicada - 12 sept 2018
Evento2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018 - San Carlos, Costa Rica
Duración: 18 jul 201820 jul 2018

Serie de la publicación

Nombre2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018 - Proceedings

Conferencia

Conferencia2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018
País/TerritorioCosta Rica
CiudadSan Carlos
Período18/07/1820/07/18

Huella

Profundice en los temas de investigación de 'Perspectives to Predict Dropout in University Students with Machine Learning'. En conjunto forman una huella única.

Citar esto