The Role of Time-Varying Contextual Factors in Latent Attrition Models for Customer Base Analysis

Patrick Bachmann (), Markus Meierer () and Jeffrey Näf ()
Additional contact information
Patrick Bachmann: University Research Priority Program Social Networks, University of Zurich, 8050 Zurich, Switzerland
Markus Meierer: University Research Priority Program Social Networks, University of Zurich, 8050 Zurich, Switzerland
Jeffrey Näf: Department of Mathematics, Eidgenössische Technische Hochschule (ETH) Zurich, 8092 Zurich, Switzerland

Marketing Science, 2021, vol. 40, issue 4, 783-809

Abstract: Customer base analysis of noncontractual businesses builds on modeling purchases and latent attrition. With the Pareto/NBD model, this has become a straightforward exercise. However, this simplicity comes at a price. Customer-level predictions often lack precision. This issue can be addressed by acknowledging the importance of contextual factors for customer behavior. Considering contextual factors might contribute in two ways: (1) by increasing predictive accuracy and (2) by identifying the impact of these determinants on the purchase and attrition process. However, there is no generalization of the Pareto/NBD model that incorporates time-varying contextual factors. Preserving a closed-form maximum likelihood solution, this study proposes an extension that facilitates modeling time-invariant and time-varying contextual factors in continuous noncontractual settings. These contextual factors can influence the purchase process, the attrition process, or both. The authors further illustrate how to control for endogenous contextual factors. Benchmarking with three data sets from the retailing industry shows that explicitly modeling time-varying contextual factors significantly improves the accuracy of out-of-sample predictions for future purchases and latent attrition.

Keywords: probability models; Pareto/NBD; customer relationship management; latent attrition; contextual factors; customer lifetime value (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://dx.doi.org/10.1287/mksc.2020.1254 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormksc:v:40:y:2021:i:4:p:783-809

Access Statistics for this article

More articles in Marketing Science from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().