Estudio comparativo de técnicas de minería de datos para develar patrones de desempeño académico en enseñanza media

The data mining techniques allow for unveiling knowledge from large volumes of information, which have recently been explored in information analysis by educational institutions but already with an increasing demand for this sector to support decision-making. In this research, a methodology for comparing data mining techniques is proposed, which is to be applied to the analysis of academic patrons in students of media education. The experiments are carried out in a dataset of 285 instances and 36 attributes obtained from an educational survey applied to the students of the School of Education of the University of Barcelona 2017-2018. Keywords: academic performance patterns; feature selection; classifiers; multiple classifier; Matlab. 1.Introducción En la actualidad se vive en un mundo digitalizado, lo cual ha generado un explosivo crecimiento en el volumen de datos, que no siempre supone un aumento de conocimiento; como lo sostiene (Fayyad et al., 1996), y en varias áreas de la academia, ciencia y empresa (Alvarado-Pérez et al., 2015) procesar los datos con métodos clásicos resulta ser en muchos casos imposible, sumamente tedioso y con resultados superficiales e insatisfactorios.