Logo do repositório
 
Publicação

Comparative analysis of machine learning models for customer segmentation in E-commerce: a data-driven approach

2026Comunicação em conferência Acesso restrito
Ver registo simples
datacite.subject.fosCiências Sociais
datacite.subject.sdg04:Educação de Qualidade
dc.contributor.authorCosta, José Paulo
dc.contributor.authorCoelho, Ana Sofia
dc.contributor.authorMartins, Oliva M.D.
dc.date.accessioned2026-03-05T11:44:05Z
dc.date.available2026-03-05T11:44:05Z
dc.date.issued2026
dc.descriptionSpringer Nature Link. Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 1695))
dc.description.abstractE-commerce growth has led to vast amounts of customer data, making effective customer segmentation crucial for personalized marketing and customer relationship management. This paper presents a comparative study of unsupervised clustering algorithms for segmenting e-commerce customers based on RFM (Recency, Frequency, Monetary) attributes and additional behavioural factors such as customer satisfaction and tenure. We evaluate multiple clustering techniques – including K-Means, hierarchical clustering, and DBSCAN – to identify which algorithm yields the most coherent and well-separated customer groups. Cluster validity is assessed using internal metrics, notably the silhouette coefficient and the Davies-Bouldin index, to determine the optimal number of clusters and the quality of results for each method. Experimental results on real e-commerce data show that the choice of clustering algorithm significantly impacts segment formation. K-Means clustering achieved the highest silhouette score and lowest Davies-Bouldin index, indicating the best overall performance in capturing distinct customer segments. A detailed profile analysis of the resulting clusters reveals interpretable segments (e.g., high-value loyal customers, at-risk customers, new customers) with apparent differences in purchasing behaviour, satisfaction levels, and customer tenure. These findings provide insights into the strengths of different clustering approaches for customer segmentation and offer practical guidance for e-commerce firms to enhance customer targeting and retention strategies.por
dc.identifier.citationCosta, P.; Coelho, A. S.; Martins, O.M.D. (2026). Comparative analysis of machine learning models for customer segmentation in e-commerce: a data-driven approach. In 5th International Conference in Information Technology & Education. Springer, Cham. DOI: /10.1007/978-3-032-09074-4_52
dc.identifier.doi10.1007/978-3-032-09074-4_5
dc.identifier.urihttp://hdl.handle.net/10198/35960
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer Nature
dc.relation.hasversionhttps://link.springer.com/chapter/10.1007/978-3-032-09074-4_52#citeas
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectCustomer segmentation
dc.subjectUnsupervised clustering
dc.subjecte-commerce ·
dc.subjectRFM analysis
dc.subjectSilhouette coefficient
dc.subjectDavies-Bouldin index
dc.titleComparative analysis of machine learning models for customer segmentation in E-commerce: a data-driven approacheng
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferenceDate2025
oaire.citation.endPage541
oaire.citation.startPage530
oaire.citation.titleThe 5th International Conference in Information Technology & Education
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameCoelho
person.familyNameMartins
person.givenNameAna Sofia
person.givenNameOliva M.D.
person.identifier2270676
person.identifier1025091
person.identifier.ciencia-idBC1C-630F-3EA4
person.identifier.ciencia-id221F-FF93-8879
person.identifier.orcid0000-0003-3389-3231
person.identifier.orcid0000-0002-2958-691X
person.identifier.ridJ-5951-2015
person.identifier.scopus-author-id55324743500
relation.isAuthorOfPublication111469c0-b9b7-4769-ba84-5e501efb9534
relation.isAuthorOfPublicationfaaf8b5a-a36d-41ef-89e1-34772e67a535
relation.isAuthorOfPublication.latestForDiscovery111469c0-b9b7-4769-ba84-5e501efb9534

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Perspectives and trends Springer_Lecture notes 2025_Submetido.pdf
Tamanho:
3.83 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.75 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus