Customer - Churn Analysis

About

Churn is typically defined as

<MATH> \text{churn} = \frac{ \text{the number of churned customers} }{ \text{total customers}} </MATH>

Churn can be deceiving especially if your growth is accelerating (it will look lower than it actually is).

A customer churn:

• from a online store: When a customer stops buying from a business
• for a service company: rupture of contract

When a customer churns, you are impacting your growth negatively.

Churn is typically rare but quite costly

Model

In a churn model:

• The highest customers are the reliable customers.
• The lowest customers are unlikely to come back.
• The customers around 50% probability are at risk of churning,

Usage

• marketing campaigns (targeted to gain back the customers with a churn risk)
• order fulfillment prioritization,
• customer support.

Documentation / Reference

• Churn Analysis as outlier detection (e.g. Mamitsuka and Abe ’00).
• Cam Davidson-Pilon 11/14/2017 HOW SHOPIFY MERCHANTS CAN MEASURE RETENTION