User Churn Model in E-Commerce Retail

Simple item page
dc.contributor.authorFridrich, Martincs
dc.contributor.authorDostál, Petrcs
dc.coverage.issue1cs
dc.coverage.volume30cs
dc.date.issued2022-04-05cs
dc.description.abstractIn e-commerce retail, maintaining a healthy customer base through retention management is necessary. Churn prediction efforts support the goal of retention and rely upon dependent and independent characteristics. Unfortunately, there does not appear to be a consensus regarding a user churn model. Thus, our goal is to propose a model based on a traditional and new set of attributes and explore its properties using auxiliary evaluation. Individual variable importance is assessed using the best performing modeling pipelines and a permutation procedure. In addition, we estimate the effects on the performance and quality of a feature set using an original technique based on importance ranking and information retrieval. The performance benchmark reveals satisfying pipelines utilizing LR, SVM-RBF, and GBM learners. The solutions rely profoundly on traditional recency and frequency aspects of user behavior. Interestingly, SVM-RBF and GBM exploit the potential of more subtle elements describing user preferences or date-time behavioural patterns. The collected evidence may also aid business decision-making associated with churn prediction efforts, e.g., retention campaign design.en
dc.formattextcs
dc.format.extent1-12cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationScientific Papers of the University of Pardubice, Series D. 2022, vol. 30, issue 1, p. 1-12.en
dc.identifier.doi10.46585/sp30011478cs
dc.identifier.issn1804-8048cs
dc.identifier.orcid0000-0002-7871-4789cs
dc.identifier.other177514cs
dc.identifier.urihttp://hdl.handle.net/11012/204120
dc.language.isoencs
dc.publisherUniv Pardubice, Fac Economics Admcs
dc.relation.ispartofScientific Papers of the University of Pardubice, Series Dcs
dc.relation.urihttps://editorial.upce.cz/1804-8048/30/1/1478cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1804-8048/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectUser Modelen
dc.subjectChurn Predictionen
dc.subjectCustomer Relationship Managementen
dc.subjectElectronic Commerceen
dc.subjectRetailen
dc.subjectMachine Learningen
dc.subjectFeature Importanceen
dc.subjectFeature Set Importanceen
dc.titleUser Churn Model in E-Commerce Retailen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-177514en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:43:30en
sync.item.modts2025.01.17 18:34:13en
thesis.grantorVysoké učení technické v Brně. Fakulta podnikatelská. Ústav informatikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SciPap01478.pdf
Size:
427.56 KB
Format:
Adobe Portable Document Format
Description:
SciPap01478.pdf
Download
Collections
Ústav informatiky