Retention Futility: Targeting High-Risk Customers Might Be Ineffective

For your marketing

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.

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.

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.

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.

Research sources

Journal of Marketing Research abstract and author-hosted paper; experiment count and targeting comparison are reported by the journal.