Build an Anomaly-Detection Pipeline for Pharma Cold-Chain Logistics
Overview
What this challenge is about.
Engineer features from 60,000 pharma shipments, train an anomaly-detection model, and tune it for high precision and recall. Get a verifiable certificate.
The Brief
What you'll do, and what you'll demonstrate.
Replace threshold-rule alerting with a triage model that hits precision above 0.9 on 'reject' and recall above 0.95 on excursions.
Earning criteria — what you'll demonstrate
- Engineer time-series features informed by domain knowledge
- Compare distance, density, and reconstruction-based anomaly methods
- Select operating points using precision-recall trade-offs
- Quantify the business impact of a model in monetary terms
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 paths this builds toward
Canonical rolesMachine Learning Engineer
Shipping an anomaly model with an explicit operating point and a business memo is exactly what a junior MLE owns in their first project.
This challenge sharpens
- anomaly-detection
- model-evaluation
- python
Data Scientist
Domain-informed feature engineering on noisy real-world sensors is a classic data-scientist deliverable.
This challenge sharpens
- feature-engineering
- time-series
- anomaly-detection
Applied AI Scientist
Translating a model improvement into euros saved is the hallmark of applied-AI-scientist communication.
This challenge sharpens
- model-evaluation
- thresholding
- anomaly-detection