Variables Influencing University Dropout: a Machine Learning-Based Study

• Irene Díaz ^[1] ; Bernardo, Ana B. ^[1] ; María Esteban ^[1] ; Rodríguez-Muñiz, Luis J. ^[1]
  1. [1] Universidad de Oviedo

     Universidad de Oviedo

     Oviedo, España

     
• Localización: The 11th International Conference on EUropean Transnational Educational: (ICEUTE 2020) / Álvaro Herrero Cosío (ed. lit.) , Carlos Cambra Baseca (ed. lit.) , Daniel Urda Muñoz (ed. lit.) , Javier Sedano Franco (ed. lit.) , Héctor Quintián Pardo (ed. lit.) , Emilio Santiago Corchado Rodríguez (ed. lit.) , 2021, ISBN 3-030-57798-8, págs. 94-103
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • University dropout is a growing problem having considerable aca-demic, social and economic consequences. It may depend on several factors,such as for example the knowledge area. In previous works we studied dropoutand transfer paths using machine learning, obtaining several key factors that arepredictive for analyzing drop out and transfer paths patterns. In this work wedelve into this topic, making a more exhaustive study using again machinelearning. Results show that Polynomial SVM is the method that obtains thehighest performance for predicting university dropout. On the other hand, it ispossible to identify the key factors affecting university dropout, showing inaddition different factors depending on thefield of study.