Quadratic vector support machine algorithm, applied to prediction of university student satisfaction

• Autores: León Velarde, César Gerardo, Chamorro-Atalaya, Omar, Morales-Romero, Guillermo, Meza-Chaupis, Yeferzon, Auqui-Ramos, Elizabeth, Ramos-Cruz, Jesús, Aybar-Bellido, Irma
• Formato: artículo
• Fecha de Publicación: 2022
• Institución: Universidad Tecnológica del Perú
• Repositorio: UTP-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.utp.edu.pe:20.500.12867/5880
• Enlace del recurso: https://hdl.handle.net/20.500.12867/5880; http://doi.org/10.11591/ijeecs.v27.i1.pp139-148
• Nivel de acceso: acceso abierto
• Materia: Predictive analytics; Student satisfaction; University students; https://purl.org/pe-repo/ocde/ford#2.02.03; https://purl.org/pe-repo/ocde/ford#5.03.01

This study aims to identify the most optimal supervised learning algorithm to be applied to the prediction of satisfaction of university students. In this study, the IBM SPSS-25.0 software was used to test the reliability of the satisfaction questionnaire and the MATLAB R2021b software through the classification learner technique to determine the supervised learning algorithm. The experimental results determine a Cronbach's Alpha reliability of 0.979, in terms of the classification algorithm, it is validated that the quadratic vector support machine (SVM) has better performance metrics, being correct in 97.8% (accuracy) in the predictions of satisfaction of university students, with a recall (sensitivity) of 96.5% and an F1 score of 0.968. Likewise, when evaluating the classification model by means of the receiver operating characteristic curve (ROC) technique, it is identified that for the three expected classes of satisfaction the value of the area under the curve (AUC) is equal to 1, in such sense the predictive model through the SVM Quadratic algorithm, has a high capacity to distinguish between the 3 classes; i) dissatisfied, ii) satisfied and iii) very satisfied of satisfaction of university students.