Redes neuronales artificiales para pronosticar el rendimiento académico de alumnos de ingeniería de sistemas e informática de la Universidad Nacional de la Amazonía Peruana

• Autores: Puga de la Cruz, Jorge, Torres Monzon, Rony
• Formato: tesis de maestría
• Fecha de Publicación: 2023
• Institución: Universidad Nacional De La Amazonía Peruana
• Repositorio: UNAPIquitos-Institucional
• Lenguaje: español
• OAI Identifier: oai:repositorio.unapiquitos.edu.pe:20.500.12737/9204
• Enlace del recurso: https://hdl.handle.net/20.500.12737/9204
• Nivel de acceso: acceso abierto
• Materia: Inteligencia artificial; Redes neuronales de la computación; Eficiencia de la educación; Estudiante universitario; https://purl.org/pe-repo/ocde/ford#2.02.04

In the research carried out on the prediction of academic performance in the Linear Algebra course at the Faculty of Systems Engineering and Informatics of the National University of the Peruvian Amazon, an attempt was made to determine if machine learning techniques could improve the accuracy of identification. of passing and failing students. Applied research with a predictive level was carried out using all available electronic data and tools such as MATLAB Neural Network Toolbox and MS Excel were used for analysis, as well as artificial neural networks. The results indicated a precision of 97.6%, a completeness of 100% and an accuracy of 97.9%, with a %E of 2.083 and a CE of 0.196274, surpassing the results obtained in similar studies. In conclusion, the research showed that machine learning techniques are effective in predicting academic performance in the Linear Algebra course, obtaining superior results to those of similar studies.