Telecom customer churn predictor

The brief

A telecom operator loses customers every month to rivals. The retention team wants to know who is likely to leave next month and what offer might keep them. Good looks like: a model that ranks customers by churn risk better than guesswork, the main reasons behind churn, and a retention list with suggested actions.

What you will build

1. Explore churn by plan, tenure and services
2. Prepare features and train classifiers
3. Pick a threshold based on the cost of a retention offer
4. Explain the top churn drivers
5. Produce a retention list and a one-page summary for managers

Free, open data to build it with

• Telco Customer Churn ↗ Kaggle

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.