← Back to Portfolio

Customer Churn & Retention: A Predictive Risk Model

A predictive churn model on 7,000+ telecom subscriber records, quantifying revenue at risk and identifying the highest-leverage retention actions.

26.5%Baseline churn rate
$139K/moRecurring revenue at risk
0.845Random forest AUC
~50%Of churners caught in top 20% risk

Overview

Built a predictive churn model on a 7,043-customer telecom subscriber base to flag at-risk accounts before they cancel, then translated the model's output into a monthly revenue-at-risk figure and a prioritized retention list — the kind of deliverable a subscription or membership business would hand straight to its retention team.

Method

Results

Bar charts showing churn rate by contract type and by customer tenure
Churn concentrates heavily in month-to-month contracts and in the first 6 months of a customer's tenure.
Horizontal bar chart of the top 10 churn drivers by random forest feature importance
Top 10 churn drivers by random forest feature importance — tenure and contract length dominate.
Model comparison on the held-out test set (1,761 customers)
ModelAccuracyPrecisionRecallF1AUC
Logistic Regression75.0%51.9%79.7%0.6280.846
Random Forest75.5%52.4%80.7%0.6360.845

Key Findings

Deliverable

Full analysis delivered as a Jupyter notebook — data pipeline, model comparison, driver analysis, and a prioritized customer risk list — with embedded outputs and charts.