Build an Anomaly-Detection Pipeline for Pharma Cold-Chain Logistics
Overview
What this challenge is about.
Build an Anomaly-Detection Pipeline for Pharma Cold-Chain Logistics. Advanced challenge in code. Writing production code that solves real engineering problem...
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.
This is not a coding exercise. It is the work a software engineer does between a Jira ticket and a merged PR. That distinction matters to every hiring manager who has seen candidates solve LeetCode problems and none who have shipped production code under real constraints.
When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."
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.
Data Mining and Knowledge Discovery
Master · Data Engineering
Strong alignment
This challenge maps to Data Mining and Knowledge Discovery at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Anomaly Detection
Apply anomaly detection to solve real industry problems and demonstrate production-level capability.
- Feature Engineering
Apply feature engineering to solve real industry problems and demonstrate production-level capability.
- Time Series
Apply time series to solve real industry problems and demonstrate production-level capability.
- Model Evaluation
Apply model evaluation to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
- Thresholding
Apply thresholding to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Machine 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