Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Urbe. Revista Brasileira de Gestão Urbana |
Texto Completo: | https://periodicos.pucpr.br/Urbe/article/view/28154 |
Resumo: | Whereas passenger demand is one of the main risks in passenger transport infrastructure projects on track, this paper aims to propose a demand forecasting model based on artificial neural networks (ANN) in order to contribute to the project management still in its early planning stages. For this, the design of ex post facto type was used in a descriptive research with quantitative approach, where the research group was composed by subway and train stations in the metropolitan region of São Paulo-Brazil. In total, 12 ANN were proposed architectures with 15 different configurations, totalling 180 training processes, testing and validation. For each architecture has been identified the lowest mean square error percentage obtained; and the best architecture, with a hidden layer, was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrolment; the number of jobs; and per capita income. With the proposed model, one expects to contribute to the theory by adding to demand forecasting models using a robust methodology and, for managers, serve as a tool in studies of economic and financial viability of these projects, still in its planning phase anticipated as an investment decision-making tool. |
id |
PUC_PR-27_5feb6bdaf86b28ddf832e5de9ce4d823 |
---|---|
oai_identifier_str |
oai:ojs.periodicos.pucpr.br:article/28154 |
network_acronym_str |
PUC_PR-27 |
network_name_str |
Urbe. Revista Brasileira de Gestão Urbana |
repository_id_str |
|
spelling |
Demand Forecasting model based on artificial neural networks for Passenger Transportation ProjectsProject Management. Early Project Planning. Demand Forecasting. Artificial Neural Networks.Whereas passenger demand is one of the main risks in passenger transport infrastructure projects on track, this paper aims to propose a demand forecasting model based on artificial neural networks (ANN) in order to contribute to the project management still in its early planning stages. For this, the design of ex post facto type was used in a descriptive research with quantitative approach, where the research group was composed by subway and train stations in the metropolitan region of São Paulo-Brazil. In total, 12 ANN were proposed architectures with 15 different configurations, totalling 180 training processes, testing and validation. For each architecture has been identified the lowest mean square error percentage obtained; and the best architecture, with a hidden layer, was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrolment; the number of jobs; and per capita income. With the proposed model, one expects to contribute to the theory by adding to demand forecasting models using a robust methodology and, for managers, serve as a tool in studies of economic and financial viability of these projects, still in its planning phase anticipated as an investment decision-making tool.Pontifícia Universidade Católica do Paraná - PUCPR2021-01-22info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.pucpr.br/Urbe/article/view/28154Revista Brasileira de Gestão Urbana; Vol. 13 (2021)Revista Brasileira de Gestão Urbana; Vol. 13 (2021)Revista Brasileira de Gestão Urbana; v. 13 (2021)2175-3369reponame:Urbe. Revista Brasileira de Gestão Urbanainstname:Pontifícia Universidade Católica do Paraná (PUC-PR)instacron:PUC_PRporhttps://periodicos.pucpr.br/Urbe/article/view/28154/25149Copyright (c) 2021 Revista Brasileira de Gestão Urbanainfo:eu-repo/semantics/openAccessVasconcelos, Vagner SanchesQuevedo-Silva, FilipeRovai, Ricardo Leonardo2021-09-14T22:51:52Zoai:ojs.periodicos.pucpr.br:article/28154Revistahttp://www.scielo.br/scielo.php?script=sci_serial&pid=2175-3369&lng=pt&nrm=isONGhttps://old.scielo.br/oai/scielo-oai.phpurbe@pucpr.br2175-33692175-3369opendoar:2021-09-14T22:51:52Urbe. Revista Brasileira de Gestão Urbana - Pontifícia Universidade Católica do Paraná (PUC-PR)false |
dc.title.none.fl_str_mv |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
title |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
spellingShingle |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects Vasconcelos, Vagner Sanches Project Management. Early Project Planning. Demand Forecasting. Artificial Neural Networks. |
title_short |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
title_full |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
title_fullStr |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
title_full_unstemmed |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
title_sort |
Demand Forecasting model based on artificial neural networks for Passenger Transportation Projects |
author |
Vasconcelos, Vagner Sanches |
author_facet |
Vasconcelos, Vagner Sanches Quevedo-Silva, Filipe Rovai, Ricardo Leonardo |
author_role |
author |
author2 |
Quevedo-Silva, Filipe Rovai, Ricardo Leonardo |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Vasconcelos, Vagner Sanches Quevedo-Silva, Filipe Rovai, Ricardo Leonardo |
dc.subject.por.fl_str_mv |
Project Management. Early Project Planning. Demand Forecasting. Artificial Neural Networks. |
topic |
Project Management. Early Project Planning. Demand Forecasting. Artificial Neural Networks. |
description |
Whereas passenger demand is one of the main risks in passenger transport infrastructure projects on track, this paper aims to propose a demand forecasting model based on artificial neural networks (ANN) in order to contribute to the project management still in its early planning stages. For this, the design of ex post facto type was used in a descriptive research with quantitative approach, where the research group was composed by subway and train stations in the metropolitan region of São Paulo-Brazil. In total, 12 ANN were proposed architectures with 15 different configurations, totalling 180 training processes, testing and validation. For each architecture has been identified the lowest mean square error percentage obtained; and the best architecture, with a hidden layer, was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrolment; the number of jobs; and per capita income. With the proposed model, one expects to contribute to the theory by adding to demand forecasting models using a robust methodology and, for managers, serve as a tool in studies of economic and financial viability of these projects, still in its planning phase anticipated as an investment decision-making tool. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-22 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.pucpr.br/Urbe/article/view/28154 |
url |
https://periodicos.pucpr.br/Urbe/article/view/28154 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://periodicos.pucpr.br/Urbe/article/view/28154/25149 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2021 Revista Brasileira de Gestão Urbana info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2021 Revista Brasileira de Gestão Urbana |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Pontifícia Universidade Católica do Paraná - PUCPR |
publisher.none.fl_str_mv |
Pontifícia Universidade Católica do Paraná - PUCPR |
dc.source.none.fl_str_mv |
Revista Brasileira de Gestão Urbana; Vol. 13 (2021) Revista Brasileira de Gestão Urbana; Vol. 13 (2021) Revista Brasileira de Gestão Urbana; v. 13 (2021) 2175-3369 reponame:Urbe. Revista Brasileira de Gestão Urbana instname:Pontifícia Universidade Católica do Paraná (PUC-PR) instacron:PUC_PR |
instname_str |
Pontifícia Universidade Católica do Paraná (PUC-PR) |
instacron_str |
PUC_PR |
institution |
PUC_PR |
reponame_str |
Urbe. Revista Brasileira de Gestão Urbana |
collection |
Urbe. Revista Brasileira de Gestão Urbana |
repository.name.fl_str_mv |
Urbe. Revista Brasileira de Gestão Urbana - Pontifícia Universidade Católica do Paraná (PUC-PR) |
repository.mail.fl_str_mv |
urbe@pucpr.br |
_version_ |
1799125956100620288 |