Customer Segmentation & Uplift
2026-09-01Planned
A planned next project: move beyond ranking who will churn to grouping customers by behaviour and estimating who a retention offer would actually change.
clustering rfm uplift modeling scikit-learn
Planned: write-up coming
This write-up will be completed as the project is finished. The sections below show the problem and intended approach; results only get added once they’re real.
Problem
The churn and retail projects both end at the same frontier: knowing who is at risk or valuable is not the same as knowing who an action would change. This project will combine RFM-style behavioural segmentation with an uplift model, so a retention budget goes to persuadable customers rather than to everyone flagged as likely to leave.
Approach
Planned: behavioural clustering to describe the customer base, then an uplift model that estimates the treatment effect of a retention offer per customer, evaluated with an uplift curve rather than plain accuracy. Results will be published when the work is complete.
Result
Results will be published when the project is complete. No metrics appear here until they’re real.
demo video
a short recorded walkthrough goes here once the project is complete
What I'd do differently
Filled in honestly once the project is done, including what didn’t work and what I’d change with hindsight.
repo and notebook links will be added when the project is published