Data mining: a scholar dropout predictive model

• Published in: 2017 IEEE Mexican Humanitarian Technology Conference (MHTC) pp. 89 - 93
• Main Authors: Rodriguez Maya, Noel Enrique, Jimenez Alfaro, Abraham Jorge, Reyes Hernandez, Luis Angel, Suarez Carranza, Brian Alison, Ruiz Garduno, Jhacer Kharen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2017
• Subjects: Computational modeling; Data mining; Data models; Economics; predictive model; Predictive models; scholar dropout; Software
• DOI: 10.1109/MHTC.2017.8006421

The Scholar Dropout (SD) phenomenon in universities has been increasing in the past years, having repercussions in social, economic, and academic, aspects among others. There are different factors that affect students to leave their studies and vary according to the place where the action takes place. Data Mining (DM) is a tool that helps to identify hidden patterns through the search of patterns into the data, for example, the creation of models to describe historical data. This research presents a SD predictive model in universities; which is based in a methodology based on DM using as study case, information of the generational cohorts 2010-2015 and 2011-2016 from the Instituto Tecnologico de Zitacuaro. The results showed a predictive model with a precision above 85%. It can be established in other universities with the necessary and pertinent adjustments.