Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.

Detalhes bibliográficos
Ano de defesa: 2022
Autor(a) principal: Juliano Marçal Lopes
Orientador(a): Eduardo Mario Dias
Banca de defesa: José Luiz Antunes de Almeida, Vidal Augusto Zapparoli Castro Melo, Vinícius Muraro da Silva
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Universidade de São Paulo
Programa de Pós-Graduação: Engenharia Elétrica
Departamento: Não Informado pela instituição
País: BR
Link de acesso: https://doi.org/10.11606/T.3.2022.tde-05092022-095859
Resumo: Advances in research and development have resulted in the emergence of many new vaccines in recent decades. However, the distribution of vaccines and the fight against vaccine-preventable diseases is still a challenge for chain managers. The vaccine supply chain typically has limited budgets, difficulty controlling product temperatures, poor inventory management, and lack of protocol for high demand and uncertain situations. Mismanagement of the vaccine supply chain can lead to a disease outbreak or, at worst, a pandemic. Fortunately, a large number of vaccine supply chain challenges such as optimal dose allocation, improving vaccination strategy and inventory management, among others, can be improved through optimization approaches. Given this scenario, the objective of this work is to propose methods to reduce costs in the chain. This was done through the creation of a machine learning model to forecast demand and a stochastic optimization model to improve the distribution of immunobiologicals among Brazilian states. The models presented here, despite considering the Brazilian scenario, have the potential to have their applications extended to the vaccine supply chain in other countries. To carry out this work, first visits were carried out in five Brazilian states to understand and map the processes of the vaccine distribution chain of the Ministry of Health. This mapping allowed the solutions proposed here to be elaborated taking into account the current scenario of the chain. The developed machine learning model encompasses the use of Gradient Boosting and Random Forest Regressor techniques, and its results are used as input data for the proposed optimization model. The stochastic optimization model considers the uncertain demand of three scenarios. The results of the study show that the machine learning model presents a demand forecast with errors significantly lower than those that the chain currently presents. Furthermore, the results of the optimization model help decision makers with a suggestion of the number of doses that should be sent to each state in each of the months of the considered period, thus reducing the chance of vaccine shortages.
id USP_ba89908f2ff85a69db1d18f6c781a023
oai_identifier_str oai:teses.usp.br:tde-05092022-095859
network_acronym_str USP
network_name_str Biblioteca Digital de Teses e Dissertações da USP
repository_id_str
spelling info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesis Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states. Otimização estocástica e aprendizado de máquina aplicados na previsão de demanda, alocação e distribuição de vacinas entre os estados brasileiros. 2022-02-03Eduardo Mario DiasJosé Luiz Antunes de AlmeidaVidal Augusto Zapparoli Castro MeloVinícius Muraro da SilvaJuliano Marçal LopesUniversidade de São PauloEngenharia ElétricaUSPBR Aprendizado computacional Demand forecast Demanda (Previsão) Immunobiological demand Otimização estocástica Stochastic optimization Vaccines Vacinas (Distribuição) Advances in research and development have resulted in the emergence of many new vaccines in recent decades. However, the distribution of vaccines and the fight against vaccine-preventable diseases is still a challenge for chain managers. The vaccine supply chain typically has limited budgets, difficulty controlling product temperatures, poor inventory management, and lack of protocol for high demand and uncertain situations. Mismanagement of the vaccine supply chain can lead to a disease outbreak or, at worst, a pandemic. Fortunately, a large number of vaccine supply chain challenges such as optimal dose allocation, improving vaccination strategy and inventory management, among others, can be improved through optimization approaches. Given this scenario, the objective of this work is to propose methods to reduce costs in the chain. This was done through the creation of a machine learning model to forecast demand and a stochastic optimization model to improve the distribution of immunobiologicals among Brazilian states. The models presented here, despite considering the Brazilian scenario, have the potential to have their applications extended to the vaccine supply chain in other countries. To carry out this work, first visits were carried out in five Brazilian states to understand and map the processes of the vaccine distribution chain of the Ministry of Health. This mapping allowed the solutions proposed here to be elaborated taking into account the current scenario of the chain. The developed machine learning model encompasses the use of Gradient Boosting and Random Forest Regressor techniques, and its results are used as input data for the proposed optimization model. The stochastic optimization model considers the uncertain demand of three scenarios. The results of the study show that the machine learning model presents a demand forecast with errors significantly lower than those that the chain currently presents. Furthermore, the results of the optimization model help decision makers with a suggestion of the number of doses that should be sent to each state in each of the months of the considered period, thus reducing the chance of vaccine shortages. Os avanços em pesquisa e desenvolvimento resultaram no surgimento de muitas novas vacinas nas últimas décadas. No entanto, a distribuição de vacinas e o combate de doenças imunopreveníveis ainda é um desafio para os gestores da cadeia. A cadeia de suprimentos de vacinas normalmente possui orçamentos limitados, dificuldade em controlar a temperatura dos produtos, gerenciamento deficiente de inventário e falta de protocolo para alta demanda e situações incertas. O mau gerenciamento da cadeia de suprimentos da vacina pode levar a um surto de doença ou, na pior das hipóteses, a uma pandemia. Felizmente, um grande número de desafios da cadeia de suprimentos de vacinas, como alocação ideal de doses, melhoria da estratégia de vacinação e gerenciamento de inventário, entre outros, pode ser aprimorado por meio de abordagens de otimização. Diante desse cenário, o objetivo desse trabalho é o de propor métodos de redução de custos da cadeia. Isso se deu por meio da criação de um modelo de machine learning para previsão de demandas e um modelo de otimização estocástica para melhoria da distribuição de imunobiológicos entre estados brasileiros. Os modelos aqui apresentados, apesar de considerarem o cenário brasileiro, possuem o potencial de terem suas aplicações estendidas para a cadeia de suprimentos de vacinas de outros países. Para realização desse trabalho, primeiramente foram realizadas visitas em cinco estados brasileiros para entendimento e mapeamento dos processos da cadeia de distribuição de vacinas do Ministério da Saúde. Este mapeamento permitiu que as soluções aqui propostas fossem elaboradas levando em consideração o cenário atual da cadeia. O modelo de machine learning desenvolvido engloba o uso das técnicas de Gradient Boosting e Random Forest Regressor, e seus resultados são utilizados como dados de entrada do modelo de otimização proposto. O modelo de otimização estocástica considera a demanda incerta de três cenários. Os resultados do estudo mostram que o modelo de machine learning apresenta uma previsão da demanda com erros relevantemente mais baixos do que os que cadeia atualmente apresenta. E ainda, os resultados do modelo de otimização auxiliam os tomadores de decisão com uma sugestão do número de doses que devem sem enviados para cada estado em cada um dos meses do período considerado, reduzindo assim, a chance de falta de vacinas. https://doi.org/10.11606/T.3.2022.tde-05092022-095859info:eu-repo/semantics/openAccessengreponame:Biblioteca Digital de Teses e Dissertações da USPinstname:Universidade de São Paulo (USP)instacron:USP2023-12-21T18:16:46Zoai:teses.usp.br:tde-05092022-095859Biblioteca Digital de Teses e Dissertaçõeshttp://www.teses.usp.br/PUBhttp://www.teses.usp.br/cgi-bin/mtd2br.plvirginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.bropendoar:27212022-09-06T13:15:07Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)false
dc.title.en.fl_str_mv Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
dc.title.alternative.pt.fl_str_mv Otimização estocástica e aprendizado de máquina aplicados na previsão de demanda, alocação e distribuição de vacinas entre os estados brasileiros.
title Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
spellingShingle Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
Juliano Marçal Lopes
title_short Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
title_full Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
title_fullStr Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
title_full_unstemmed Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
title_sort Stochastic optimization and machine learning applied in the demand forecast, allocation and distribution of vaccines between Brazilian states.
author Juliano Marçal Lopes
author_facet Juliano Marçal Lopes
author_role author
dc.contributor.advisor1.fl_str_mv Eduardo Mario Dias
dc.contributor.referee1.fl_str_mv José Luiz Antunes de Almeida
dc.contributor.referee2.fl_str_mv Vidal Augusto Zapparoli Castro Melo
dc.contributor.referee3.fl_str_mv Vinícius Muraro da Silva
dc.contributor.author.fl_str_mv Juliano Marçal Lopes
contributor_str_mv Eduardo Mario Dias
José Luiz Antunes de Almeida
Vidal Augusto Zapparoli Castro Melo
Vinícius Muraro da Silva
description Advances in research and development have resulted in the emergence of many new vaccines in recent decades. However, the distribution of vaccines and the fight against vaccine-preventable diseases is still a challenge for chain managers. The vaccine supply chain typically has limited budgets, difficulty controlling product temperatures, poor inventory management, and lack of protocol for high demand and uncertain situations. Mismanagement of the vaccine supply chain can lead to a disease outbreak or, at worst, a pandemic. Fortunately, a large number of vaccine supply chain challenges such as optimal dose allocation, improving vaccination strategy and inventory management, among others, can be improved through optimization approaches. Given this scenario, the objective of this work is to propose methods to reduce costs in the chain. This was done through the creation of a machine learning model to forecast demand and a stochastic optimization model to improve the distribution of immunobiologicals among Brazilian states. The models presented here, despite considering the Brazilian scenario, have the potential to have their applications extended to the vaccine supply chain in other countries. To carry out this work, first visits were carried out in five Brazilian states to understand and map the processes of the vaccine distribution chain of the Ministry of Health. This mapping allowed the solutions proposed here to be elaborated taking into account the current scenario of the chain. The developed machine learning model encompasses the use of Gradient Boosting and Random Forest Regressor techniques, and its results are used as input data for the proposed optimization model. The stochastic optimization model considers the uncertain demand of three scenarios. The results of the study show that the machine learning model presents a demand forecast with errors significantly lower than those that the chain currently presents. Furthermore, the results of the optimization model help decision makers with a suggestion of the number of doses that should be sent to each state in each of the months of the considered period, thus reducing the chance of vaccine shortages.
publishDate 2022
dc.date.issued.fl_str_mv 2022-02-03
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://doi.org/10.11606/T.3.2022.tde-05092022-095859
url https://doi.org/10.11606/T.3.2022.tde-05092022-095859
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Universidade de São Paulo
dc.publisher.program.fl_str_mv Engenharia Elétrica
dc.publisher.initials.fl_str_mv USP
dc.publisher.country.fl_str_mv BR
publisher.none.fl_str_mv Universidade de São Paulo
dc.source.none.fl_str_mv reponame:Biblioteca Digital de Teses e Dissertações da USP
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Biblioteca Digital de Teses e Dissertações da USP
collection Biblioteca Digital de Teses e Dissertações da USP
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)
repository.mail.fl_str_mv virginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.br
_version_ 1786376585415229440