Acquisition and retention · Hidden Markov model applied to two empirical settings
Some Customers Would Rather Leave Without Saying Goodbye
Ascarza, E., Netzer, O., & Hardie, B. G. S. (2018). Marketing Science, 37(1), 54–77.
Plain-English take
Overt churners were often more active before leaving, while many silent churners disengaged early and rarely canceled formally. For your marketing: Separate cancellation from quiet nonuse when measuring churn.
How much weight to give this
3.0/5 Limited or context-dependent evidence
The 1–5 evidence-check score is a practical reading aid, not a formal peer review or a probability that a conclusion is true. It combines design strength (2 points), sample reporting (1), comparison/control clarity (1), and how much of the paper could be checked (1). Access affects how confidently this directory can assess a study, not the study's underlying quality. Blinding is reported separately because it is not relevant to every design.
The accessible description does not establish a strong causal design.
A usable sample size is not stated in the profile's accessible source.
Comparison or control details are limited in the reviewed source.
An accessible full paper or manuscript is linked, making methods easier to check.
Double-blind? Not applicable in the same way as a participant-treatment experiment.
Research question
What the authors investigated
How should firms distinguish customers who formally cancel from those who silently disengage?
Design
The authors develop a hidden Markov model for overt and silent churn and apply it to a daily-deal website and a performing-arts organization.
Sample and setting
Two hybrid customer-relationship settings where customers can formally terminate or simply stop interacting with the firm.
Reported result
What the study found
Overt churners were often more active before leaving, while many silent churners disengaged early and rarely canceled formally. The two churn groups responded differently to communications, so one retention strategy may not suit both.
This is a paraphrase of the source. Check the original paper for definitions, estimates, statistical uncertainty and analysis details.
Scope and transfer
Limitations to keep in view
The two applications are specific to their services and datasets. The model's churn-state assumptions and communication responses should be validated for a SaaS product's billing and activity data.
Possible founder application
Separate cancellation from quiet nonuse when measuring churn. Build retention reporting that includes product inactivity and communication response rather than treating account status as the only signal.
Evidence access
Publisher abstract and author-hosted paper
Marketing Science abstract and author-hosted paper; both applications and the distinction between overt and silent churn are reported in the paper.
If only an abstract or metadata was available, the profile is limited to claims supported there. A paper's paywall does not change its evidentiary status, but it limits what we can substantiate from accessible text.