Publication detail

User Churn Model in E-Commerce Retail

FRIDRICH, M. DOSTÁL, P.

Original Title

User Churn Model in E-Commerce Retail

Type

journal article in Web of Science

Language

English

Original Abstract

In 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.

Keywords

User Model; Churn Prediction; Customer Relationship Management; Electronic Commerce; Retail; Machine Learning; Feature Importance; Feature Set Importance

Authors

FRIDRICH, M.; DOSTÁL, P.

Released

5. 4. 2022

Publisher

Univ Pardubice, Fac Economics Adm

Location

Pardubice

ISBN

1804-8048

Periodical

Scientific Papers of the University of Pardubice, Series D

Year of study

30

Number

1

State

Czech Republic

Pages from

1

Pages to

12

Pages count

12

URL

https://editorial.upce.cz/1804-8048/30/1/1478

Full text in the Digital Library

http://hdl.handle.net/11012/204120

BibTex

@article{BUT177514,
  author="Martin {Fridrich} and Petr {Dostál}",
  title="User Churn Model in E-Commerce Retail",
  journal="Scientific Papers of the University of Pardubice, Series D",
  year="2022",
  volume="30",
  number="1",
  pages="1--12",
  doi="10.46585/sp30011478",
  issn="1804-8048",
  url="https://editorial.upce.cz/1804-8048/30/1/1478"
}