At a glance
- Client
- A large omnichannel retailerName withheld for confidentiality
- Industry
- Retail
- Service
- Data & Analytics
- Scope
- Customer data platform, churn model and retention campaigns
The challenge
The retailer had tens of millions of customers but only noticed they had left months later, when purchases stopped. Retention offers went to everyone, wasting budget on loyal customers and missing those about to leave.
Customer data was split across e-commerce, stores and the loyalty programme.
Our approach
Build a single customer view
We joined online, in-store and loyalty data into one profile per customer.
Model churn risk
A machine learning model scores every customer's likelihood of leaving, refreshed daily.
Personalise the response
At-risk customers receive offers matched to what they value, not a generic discount.
Measure the lift
Control groups show exactly how many customers each campaign retains.
The solution
Marketing now sees which customers are likely to leave while there is still time to act, and why. Retention campaigns run automatically with personalised offers.
Budget goes to customers who need a reason to stay, and every campaign's effect is measured.
Results
- One customer view across online, stores and loyalty
- Daily churn risk scores for every customer
- Personalised retention offers
- Campaign impact measured against control groups
Technology used
- Customer data platform
- Python
- Gradient boosting
- Marketing automation
- Snowflake
Facing a similar challenge?
Tell us what you are working on. We will walk you through how we would approach it, with no obligation.