Pearclustering: a novel clustering algorithm with an application to bike mobility

Bike Sharing Systems (BSS) have become a key solution for urban mobility, reducing traffic-related CO2 emissions. However, managing BSS poses challenges that require data-driven solutions, particularly for understanding their global behavior and forecasting their evolution. These dynamics arise from...

ver descrição completa

Detalhes bibliográficos
Autores: Márquez Saldaña, Francisco, Aranda Corral, Gonzalo A., Borrego Díaz, Joaquín
Tipo de documento: artigo
Estado:Versión aceptada para publicación
Data de publicação:2026
País:España
Recursos:Universidad de Sevilla (US)
Repositório:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:dnet:idus________::5c4122b0c8057b4d97283fe35088a3f3
Acesso em linha:https://hdl.handle.net/11441/184183
https://doi.org/10.1007/s12065-025-01062-6
Access Level:Acceso aberto
Palavra-chave:Clustering analysis
Machine-learning in mobility
Bike sharing platforms
Artificial intelligence in engineering
id ES_dc6381a46be3bcadcb9727a7244d9acc
oai_identifier_str oai:dnet:idus________::5c4122b0c8057b4d97283fe35088a3f3
network_acronym_str ES
network_name_str España
repository_id_str
spelling Pearclustering: a novel clustering algorithm with an application to bike mobilityMárquez Saldaña, FranciscoAranda Corral, Gonzalo A.Borrego Díaz, JoaquínClustering analysisMachine-learning in mobilityBike sharing platformsArtificial intelligence in engineeringBike Sharing Systems (BSS) have become a key solution for urban mobility, reducing traffic-related CO2 emissions. However, managing BSS poses challenges that require data-driven solutions, particularly for understanding their global behavior and forecasting their evolution. These dynamics arise from the interaction among users, companies, dock stations, and city policies, influenced by sociological and infrastructure-based factors. This paper proposes a novel clustering methodology to analyze BSS data across multiple cities. By clustering station-day tuples instead of aggregating statistics, our approach captures seasonal patterns, special events, and weekday/weekend differences. Using Pearson Correlation as a distance metric, it remains robust across different station sizes and system scales. Trained on three European BSS and evaluated across six cities from 4 different countries, our model uncovers meaningful patterns such as work, residential, and leisure areas, as well as seasonal changes even in systems not used in the training process. These insights enhance BSS management, expansion, and decision-making, with applications in monitoring, anomaly detection, and demand prediction.SpringerCiencias de la Computación e Inteligencia ArtificialTIC137: Lógica, Computación e Ingeniería del Conocimiento2026info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/184183https://doi.org/10.1007/s12065-025-01062-6reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésEvolutionary Intelligence, 18 (4), 73. 10.1007/s12065-025-01062-6info:eu-repo/semantics/openAccessoai:dnet:idus________::5c4122b0c8057b4d97283fe35088a3f32026-06-17T12:51:07Z
dc.title.none.fl_str_mv Pearclustering: a novel clustering algorithm with an application to bike mobility
title Pearclustering: a novel clustering algorithm with an application to bike mobility
spellingShingle Pearclustering: a novel clustering algorithm with an application to bike mobility
Márquez Saldaña, Francisco
Clustering analysis
Machine-learning in mobility
Bike sharing platforms
Artificial intelligence in engineering
title_short Pearclustering: a novel clustering algorithm with an application to bike mobility
title_full Pearclustering: a novel clustering algorithm with an application to bike mobility
title_fullStr Pearclustering: a novel clustering algorithm with an application to bike mobility
title_full_unstemmed Pearclustering: a novel clustering algorithm with an application to bike mobility
title_sort Pearclustering: a novel clustering algorithm with an application to bike mobility
dc.creator.none.fl_str_mv Márquez Saldaña, Francisco
Aranda Corral, Gonzalo A.
Borrego Díaz, Joaquín
author Márquez Saldaña, Francisco
author_facet Márquez Saldaña, Francisco
Aranda Corral, Gonzalo A.
Borrego Díaz, Joaquín
author_role author
author2 Aranda Corral, Gonzalo A.
Borrego Díaz, Joaquín
author2_role author
author
dc.contributor.none.fl_str_mv Ciencias de la Computación e Inteligencia Artificial
TIC137: Lógica, Computación e Ingeniería del Conocimiento
dc.subject.none.fl_str_mv Clustering analysis
Machine-learning in mobility
Bike sharing platforms
Artificial intelligence in engineering
topic Clustering analysis
Machine-learning in mobility
Bike sharing platforms
Artificial intelligence in engineering
description Bike Sharing Systems (BSS) have become a key solution for urban mobility, reducing traffic-related CO2 emissions. However, managing BSS poses challenges that require data-driven solutions, particularly for understanding their global behavior and forecasting their evolution. These dynamics arise from the interaction among users, companies, dock stations, and city policies, influenced by sociological and infrastructure-based factors. This paper proposes a novel clustering methodology to analyze BSS data across multiple cities. By clustering station-day tuples instead of aggregating statistics, our approach captures seasonal patterns, special events, and weekday/weekend differences. Using Pearson Correlation as a distance metric, it remains robust across different station sizes and system scales. Trained on three European BSS and evaluated across six cities from 4 different countries, our model uncovers meaningful patterns such as work, residential, and leisure areas, as well as seasonal changes even in systems not used in the training process. These insights enhance BSS management, expansion, and decision-making, with applications in monitoring, anomaly detection, and demand prediction.
publishDate 2026
dc.date.none.fl_str_mv 2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/184183
https://doi.org/10.1007/s12065-025-01062-6
url https://hdl.handle.net/11441/184183
https://doi.org/10.1007/s12065-025-01062-6
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Evolutionary Intelligence, 18 (4), 73.
10.1007/s12065-025-01062-6
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421764550852608
score 15,812429

Registros relacionados