---
title: What is Churn prediction?
url: https://markin.ai/glossary/churn-prediction
category: Retention and churn
---

# Churn prediction

> Churn prediction estimates the probability that a given customer will stop paying within a defined horizon, using behavioural, transactional and service signals. It produces a ranking of risk; on its own it changes nothing, because a score is not an intervention.

## Why it matters for ARPU

Most enterprises already have a churn model and still lose the same customers. The gap is decisioning: choosing which at-risk customer gets which action, at what cost, and proving it worked.

## Related terms

- [Churn rate](https://markin.ai/glossary/churn-rate), Churn rate is the share of customers, or of revenue, lost in a period.
- [Propensity model](https://markin.ai/glossary/propensity-model), A propensity model estimates the probability that a customer takes an action, such as buying, upgrading or cancelling.
- [Uplift model](https://markin.ai/glossary/uplift-model), An uplift model estimates the change in outcome caused by treating a customer, rather than the outcome itself.
- [Save offer](https://markin.ai/glossary/save-offer), A save offer is an incentive presented to a customer who is about to leave: a discount, a pause, a plan downgrade or a service remedy.

## Go deeper

- [Churn prediction vs retention decisioning](https://markin.ai/compare/churn-prediction-vs-retention-decisioning), Where scoring stops.
- [Customer churn prediction guide](https://markin.ai/blog/customer-churn-prediction-guide), Building a model that earns its keep.

Source: https://markin.ai/glossary/churn-prediction