Code
Predictive Churn Model for Bangalore D2C Cosmetics
Overview
What this challenge is about.
You will analyze a provided dataset of 10k customers with features like purchase frequency, average order value, time since last purchase, pages visited, support tickets, and subscription status. Build a binary classification model (churn vs. no churn) using logistic regression or random forest. Achieve at least 0.80 AUC-ROC. Deliver a one-page executive summary explaining top 3 churn drivers and recommended actions. Constraints: use only scikit-learn, no deep learning; handle class imbalance; provide feature importance.
The Brief
What you'll do, and what you'll demonstrate.
Predict which customers will churn in the next 30 days to enable proactive retention.
Earning criteria — what you'll demonstrate
- Apply supervised learning to a real business problem
- Engineer features from raw transactional data
- Evaluate model performance using AUC-ROC and precision-recall
- Communicate model insights to non-technical stakeholders
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.
Career mappings coming soon.