An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic

Bibliographic Details
Main Author: Ashofteh, Afshin
Publication Date: 2022
Other Authors: Bravo, Jorge Miguel, Ayuso, Mercedes
Format: Article
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/138671
Summary: Ashofteh, A., Bravo, J. M., & Ayuso, M. (2022). An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic. Applied Soft Computing, 128(October), 1-17. [109422]. https://doi.org/10.2139/ssrn.4057314, https://doi.org/10.1016/j.asoc.2022.109422 ----- Fundinhg: The authors are grateful to the anonymous reviewers for their constructive comments. Afshin Ashofteh and Jorge M. Bravo were supported by Portuguese national science funds made available through the FCT under project UIDB/04152/2020-Centro de Investigação em Gestão de Informação (MagIC). Additionally, Mercedes Ayuso is grateful to the Spanish Ministry of Science and Innovation for funding received under grant PID2019-105986GB-C21 and to the Secretaria d’Universitats i Recerca del departament d’Empresa i Coneixement de la Generalitat de Catalunya for funding received under grant 2020-PANDE-00074 (research project directly related to COVID-19 and economy).
id RCAP_ba06a997a0459c5e3587377e2123c8c8
oai_identifier_str oai:run.unl.pt:10362/138671
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 PandemicLayered learningMultiple learning processesTime SeriesEnsemble Bayesian Model Averaging (EBMA)SARS-CoV-2COVID-19Bayesian model averaging (BMA)Ensemble learningForecastingPanel dataMachine learningSoftwareSDG 3 - Good Health and Well-beingAshofteh, A., Bravo, J. M., & Ayuso, M. (2022). An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic. Applied Soft Computing, 128(October), 1-17. [109422]. https://doi.org/10.2139/ssrn.4057314, https://doi.org/10.1016/j.asoc.2022.109422 ----- Fundinhg: The authors are grateful to the anonymous reviewers for their constructive comments. Afshin Ashofteh and Jorge M. Bravo were supported by Portuguese national science funds made available through the FCT under project UIDB/04152/2020-Centro de Investigação em Gestão de Informação (MagIC). Additionally, Mercedes Ayuso is grateful to the Spanish Ministry of Science and Innovation for funding received under grant PID2019-105986GB-C21 and to the Secretaria d’Universitats i Recerca del departament d’Empresa i Coneixement de la Generalitat de Catalunya for funding received under grant 2020-PANDE-00074 (research project directly related to COVID-19 and economy).Quantifying and analyzing excess mortality in crises such as the ongoing COVID-19 pandemic is crucial for policymakers. The traditional way it is measured does not account for differences in the level, long-term secular trends, and seasonal patterns in all-cause mortality across countries and regions. This paper develops and empirically investigates the forecasting performance of a novel flexible and dynamic ensemble learning strategy for seasonal time series forecasting of monthly respiratory diseases deaths data across a pool of 61 heterogeneous countries. The strategy is based on a Bayesian Model Ensemble (BME) of heterogeneous time series methods involving both the selection of the subset of best forecasters (model confidence set), the identification of the best holdout period for each contributed model, and the determination of optimal weights using the out-of-sample predictive accuracy. A model selection strategy is also developed to remove the outlier models and to combine the models with reasonable accuracy in the ensemble. The empirical results of this large set of experiments show that the accuracy of the BME approach improves noticeably by using a flexible and dynamic holdout period selection. Additionally, that the BME forecasts of respiratory disease deaths for each country are highly accurate and exhibit a high correlation (94%) with COVID-19 deaths in 2020.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNAshofteh, AfshinBravo, Jorge MiguelAyuso, Mercedes2022-05-25T22:18:17Z2022-10-012022-10-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article17application/pdfhttp://hdl.handle.net/10362/138671eng1568-4946PURE: 44265559https://doi.org/10.1016/j.asoc.2022.109422info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:01:54Zoai:run.unl.pt:10362/138671Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:32:57.386983Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
title An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
spellingShingle An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
Ashofteh, Afshin
Layered learning
Multiple learning processes
Time Series
Ensemble Bayesian Model Averaging (EBMA)
SARS-CoV-2
COVID-19
Bayesian model averaging (BMA)
Ensemble learning
Forecasting
Panel data
Machine learning
Software
SDG 3 - Good Health and Well-being
title_short An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
title_full An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
title_fullStr An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
title_full_unstemmed An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
title_sort An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic
author Ashofteh, Afshin
author_facet Ashofteh, Afshin
Bravo, Jorge Miguel
Ayuso, Mercedes
author_role author
author2 Bravo, Jorge Miguel
Ayuso, Mercedes
author2_role author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Ashofteh, Afshin
Bravo, Jorge Miguel
Ayuso, Mercedes
dc.subject.por.fl_str_mv Layered learning
Multiple learning processes
Time Series
Ensemble Bayesian Model Averaging (EBMA)
SARS-CoV-2
COVID-19
Bayesian model averaging (BMA)
Ensemble learning
Forecasting
Panel data
Machine learning
Software
SDG 3 - Good Health and Well-being
topic Layered learning
Multiple learning processes
Time Series
Ensemble Bayesian Model Averaging (EBMA)
SARS-CoV-2
COVID-19
Bayesian model averaging (BMA)
Ensemble learning
Forecasting
Panel data
Machine learning
Software
SDG 3 - Good Health and Well-being
description Ashofteh, A., Bravo, J. M., & Ayuso, M. (2022). An Ensemble Learning Strategy for Panel Time Series Forecasting of Excess Mortality During the COVID-19 Pandemic. Applied Soft Computing, 128(October), 1-17. [109422]. https://doi.org/10.2139/ssrn.4057314, https://doi.org/10.1016/j.asoc.2022.109422 ----- Fundinhg: The authors are grateful to the anonymous reviewers for their constructive comments. Afshin Ashofteh and Jorge M. Bravo were supported by Portuguese national science funds made available through the FCT under project UIDB/04152/2020-Centro de Investigação em Gestão de Informação (MagIC). Additionally, Mercedes Ayuso is grateful to the Spanish Ministry of Science and Innovation for funding received under grant PID2019-105986GB-C21 and to the Secretaria d’Universitats i Recerca del departament d’Empresa i Coneixement de la Generalitat de Catalunya for funding received under grant 2020-PANDE-00074 (research project directly related to COVID-19 and economy).
publishDate 2022
dc.date.none.fl_str_mv 2022-05-25T22:18:17Z
2022-10-01
2022-10-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/138671
url http://hdl.handle.net/10362/138671
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 1568-4946
PURE: 44265559
https://doi.org/10.1016/j.asoc.2022.109422
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 17
application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596777615327232