Retention Futility: Targeting High-Risk Customers Might be Ineffective

Abstract

Companies in a variety of sectors are increasingly managing customer churn proactively, generally by detecting customers at the highest risk of churning and targeting retention efforts towards them. While there is a vast literature on developing churn prediction models that identify customers at the highest risk of churning, no research has investigated whether it is indeed optimal to target those individuals. Combining two field experiments with machine learning techniques, the author demonstrates that customers identified as having the highest risk of churning are not necessarily the best targets for proactive churn programs. This finding is not only contrary to common wisdom but also suggests that retention programs are sometimes futile not because firms offer the wrong incentives but because they do not apply the right targeting rules. Accordingly, firms should focus their modeling efforts on identifying the observed heterogeneity in response to the intervention and to target customers on the basis of their sensitivity to the intervention, regardless of their risk of churning. This approach is empirically demonstrated to be significantly more effective than the standard practice of targeting customers with the highest risk of churning. More broadly, the author encourages firms and researchers using randomized trials (or A/B tests) to look beyond the average effect of interventions and leverage the observed heterogeneity in customers' response to select customer targets.

Heterogeneous Employment Effects of Job Search Programmes: A Machine Learning Approach

“…The negative employment effect of the current assignment mechanism would be reduced by 21% (= �(0.82 − 0.61)/0.82� • 100%). These results are consistent with the argument that assignments based on expected treatment effects rather than on predicted outcomes can be more successful (Ascarza, 2016). However, the average effects remain negative and the programme does not seem useful in improving the employment opportunities of unemployed persons in general.…”

A bi‐objective procedure to deliver actionable knowledge in sport services

“…This work extends the previous works of Pinheiro and Cavique (2015, 2018, 2019a, 2019b and complements the survival analysis studies proposed by Sobreiro (Sobreiro, Pinheiro, & Santos, 2018), (Sobreiro et al, 2019). These works fill a gap in the study of retention through the use of machine learning techniques in regular sports services.…”

Response transformation and profit decomposition for revenue uplift modeling

“…Therefore, a targeting model must identify those customers who have no intention to buy but can be persuaded to buy through a discount. This is the aim of an uplift model, while a response model could only predict the buying propensity of customers, which is less useful for targeting (e.g., Ascarza, 2018).…”