2026-06-10T08:57:49Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/109392025-10-09T00:05:32Zcom_10259_5645com_10259_5086com_10259_2604com_10259_6193com_10259_4147com_10259.4_106col_10259_10943col_10259_7108

2025-10-08T08:14:40Z urn:hdl:10259/10939 Time management and absenteeism: studying the students through machine learning Porras Alfonso, Santiago Sauvée, Athénaïs Puche Regaliza, Julio César Casado Yusta, Silvia Antón Maraña, Paula Pacheco Bonrostro, Joaquín Absenteeism Higher education Support vector machine Explainable artificial intelligence Shapley additive explanation Time management Absenteeism in higher education is a problem that may involve institutional, economic, social, and individual consequences. The present work aims to analyse whether the way students manage their personal time could be an explanation for absenteeism rates. Authors used machine learning based methodology, combined with explainable artificial intelligence methods. This allowed them to design a two-levels analysis, it is to say from a global, and an individual perspective. Factors such as repeating a course have the most negative impact over class attendance. On the contrary, being able to submit an assignment before the deadline has the most positive impact over class attendance. The kind of academic career, the place of living or the hobbies has also influence over the absenteeism. 2025-10-08T08:14:40Z 2025-10-08T08:14:40Z 2024-06 info:eu-repo/semantics/conferenceObject 978-84-13962-00-9 https://hdl.handle.net/10259/10939 10.4995/HEAd24.2024.17343 eng 10th International Conference on Higher Education Advances (HEAd’24), p. 673-680 https://doi.org/10.4995/HEAd24.2024.17343 http://creativecommons.org/licenses/by-nc-sa/4.0/ info:eu-repo/semantics/openAccess Atribución-NoComercial-CompartirIgual 4.0 Internacional Editorial Universitat Politècnica de València