Acquisition and retention · Two field experiments combined with machine-learning targeting methods
Retention Futility: Targeting High-Risk Customers Might Be Ineffective
Ascarza, E. (2018). Journal of Marketing Research, 55(1), 80–98.
Plain-English take
Customers with the highest predicted churn risk were not necessarily the best targets. For your marketing: Use treatment response or expected incremental profit to select retention audiences, rather than ranking only by churn propensity.
How much weight to give this
4.0/5 Useful evidence with meaningful caveats
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.
An experiment is useful for causal evidence, but the accessible profile does not establish random assignment.
A usable sample size is not stated in the profile's accessible source.
Experimental comparison is described; randomization or control details need checking in the paper.
An accessible full paper or manuscript is linked, making methods easier to check.
Double-blind? Blinding is not reported in the source reviewed; that does not establish whether blinding was or was not used.
Research question
What the authors investigated
Are customers most likely to churn also the best customers to target with a retention intervention?
Design
The author combines two field experiments with machine-learning techniques to compare targeting by predicted churn risk with targeting by expected response to retention efforts.
Sample and setting
Two field experiments involving customer retention interventions; the publisher abstract does not summarize sample sizes or industries.
Reported result
What the study found
Customers with the highest predicted churn risk were not necessarily the best targets. The response-based targeting approach was significantly more effective than standard targeting of the highest-risk customers.
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
Two specific field experiments and intervention settings; targeting performance depends on treatment response and available data. High churn risk and high persuadability are different quantities.
Possible founder application
Use treatment response or expected incremental profit to select retention audiences, rather than ranking only by churn propensity. Hold out customers so the intervention's causal effect can be estimated.
Evidence access
Publisher abstract and author-hosted paper
Journal of Marketing Research abstract and author-hosted paper; experiment count and targeting comparison are reported by the journal.
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.