TY - JOUR
T1 - Prediction of university dropout through technological factors: A case study in Ecuador
AU - Alban Taipe, Mayra Susana
AU - Mauricio Sánchez, David
PY - 2018/1/1
Y1 - 2018/1/1
N2 - © 2018. Predicting dropout in universities has become a concern in several countries around the world. With the introduction of new information and communication technologies, new factors have appeared that influence student dropout in universities. This article proposes an approach to machine learning based on logistic regression techniques and decision trees and factors such as Internet addiction, addiction to social networks and addiction to technology, that affect the desertion of students in universities. As a result, it was obtained that the technique with the highest percentage of dropout precision was decision trees with 91.70%.
AB - © 2018. Predicting dropout in universities has become a concern in several countries around the world. With the introduction of new information and communication technologies, new factors have appeared that influence student dropout in universities. This article proposes an approach to machine learning based on logistic regression techniques and decision trees and factors such as Internet addiction, addiction to social networks and addiction to technology, that affect the desertion of students in universities. As a result, it was obtained that the technique with the highest percentage of dropout precision was decision trees with 91.70%.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85058960432&origin=inward
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85058960432&origin=inward
M3 - Article
SN - 0798-1015
JO - Espacios
JF - Espacios
ER -