Comparison between Multiple Linear Regression Models Vs Supervised Artificial Neural Networks in the Prediction of Ecuadorian Ser Bachiller 2018-2019 Grades

Abstract

The article deals with the comparison between Multiple Linear Regression models vs supervised Artificial Neural Networks in the prediction of academic performance in the form of grades of the Ser-Bachiller evaluation of Ecuador, period 2018-2019. This by testing assumptions and calculating adequacy measures to identify the best prediction method. To meet the objective, information from the results of the Ser-Bachiller tests of Ecuador in the 2018-2019 cycle whose database is located on the official website of the National Institute of Educational Evaluation was used. There were 514852 students evaluated from all over the country. With this information we compared models that predict the scores in the domains of Mathematics, Linguistics, Science and Social Sciences, through factors associated with academic performance of Institutional, Pedagogical, Psychosocial and sociodemographic type.