Construcción de un modelo para predecir el rendimiento académico de los estudiantes de ingeniería electrónica de la Universidad Distrital Francisco José de Caldas mediante algoritmos de redes neuronales con aprendizaje automático

Abstract

This work seeks to develop an academic performance prediction model using neural network algorithms with machine learning, developed in the electronic engineering career of the Francisco José de Caldas District University, data collection is done through the office of Systems consultancy of the District University where the anonymous data of the people admitted between the years 2008 to 2020 and their career path are obtained, the variables associated with the different factors, are collected, defined, compared, classified and selected for then train the chosen machine learning algorithms. The performance measures of these are analyzed and the required adjustments are made, to proceed to carry out a cross-validation of the model, this in order to provide support for future research that seeks to control academic performance and reduce the rates. associated as desertion.