Data Mining Model to Predict Academic Performance at the Universidad Nacional de Colombia


Data Mining Model to Predict Academic Performance at the Universidad Nacional de Colombia
Published in:	Innovation in Engineering, Technology and Education for Competitiveness and Prosperity: Proceedings of the 12th Latin American and Caribbean Conference for Engineering and Technology
Date of Conference:	July 21-24,2014
Location of Conference:	Guayaquil,Ecuador
Authors:	Camilo Ernesto López Guarín Elizabeth León Guzmán Fabio González Osorio
Refereed Paper:	#131

Abstract:
This paper presents the results of applying an educational data mining approach to model academic attrition (loss of academic status) at the Universidad Nacional de Colombia. Two data mining models were defined to analyze academic data. The models use two classification techniques, naïve Bayes and J-48, a decision tree classifier, in order to acquire a better understanding of the attrition during the first enrollments and to assess the quality of the data for the classification task, which can be understood as the prediction of the loss of academic status due to low academic performance. Different models were built to predict the loss of academic status in different scenarios including: attrition in any of the first four enrollments; at a specific enrollment using as input the admission process data and also using the historical academic records. Experimental results show that the prediction of the loss of academic status is improved when academic data is added.