Cluster a Telco's Subscriber Base for a Pricing Refresh
Overview
What this challenge is about.
You receive 12 months of anonymized subscriber-level data: monthly minutes, SMS, mobile data, top-up frequency, top-up amount, churn flag, and tenure. Clean and feature-engineer the data, then run at least two clustering approaches (e.g., k-means after standardization and a hierarchical method or HDBSCAN) and validate stability with bootstrap resampling. Pick a final k between 3 and 6, profile each cluster in plain English, and recommend a refreshed tier structure. Success is a deck the head of marketing can present to the executive committee with named personas and projected revenue impact.
The Brief
What you'll do, and what you'll demonstrate.
Identify 3-6 behaviorally distinct subscriber segments and propose a refreshed prepaid tier structure that reduces cannibalization.
Earning criteria — what you'll demonstrate
- Apply preprocessing and feature scaling appropriate to behavioral data
- Compare multiple clustering algorithms and select with stability evidence
- Translate cluster centroids into named, interpretable personas
- Connect a segmentation to a concrete business action (pricing)
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Data Scientist
Behavioral segmentation tied to a pricing decision is a canonical junior-data-scientist first project in any consumer-facing business.
This challenge sharpens
- clustering
- segmentation
- exploratory-data-analysis
Applied AI Scientist
Stability analysis plus business framing mirrors applied AI work in product or consumer teams.
This challenge sharpens
- clustering
- scikit-learn
- segmentation
AI Product Manager
Translating cluster outputs into pricing tiers and revenue impact maps directly onto AI product manager interview cases.
This challenge sharpens
- segmentation
- exploratory-data-analysis
- feature-engineering