Absences Predictive Model of for the Outpatient Unit in a Public Hospital

D. M. Rivero-Albarrán, F. I. Rivas-Echeverría, P. M. Villareal, S. M. Arciniegas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


The quality must be present external in consultation services, either to satisfy the needs of the users and/or to maximize the use of the resources. For this reason, administrators require the necessary information and knowledge to support them in decision-making processes. This paper presents a time series-based model, to predict absenteeism and attendance at the outpatient service. The CRISP-DM methodology, typical of data analytics, was used to explore the models. It was found that the ARIMA model was the one that obtained the lowest absolute and quadratic error. In addition, based on the time series predictions, it was determined that the number of absences to external medicine consultations is around 10% per day. This information can be used to reduce the attention time lost due to absences.

Original languageEnglish
Title of host publicationCommunication and Smart Technologies - Proceedings of ICOMTA 2021
EditorsÁlvaro Rocha, Daniel Barredo, Paulo Carlos López-López, Iván Puentes-Rivera
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages10
ISBN (Print)9789811657917
StatePublished - 2022
EventInternational Conference on Communication and Applied Technologies, ICOMTA 2021 - Bogotá, Colombia
Duration: 1 Sep 20213 Sep 2021

Publication series

NameSmart Innovation, Systems and Technologies
Volume259 SIST
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026


ConferenceInternational Conference on Communication and Applied Technologies, ICOMTA 2021

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.


  • Data analytics
  • External consultation services
  • Time series


Dive into the research topics of 'Absences Predictive Model of for the Outpatient Unit in a Public Hospital'. Together they form a unique fingerprint.

Cite this