Spectral Clustering for an Urban-Mobility Operator's Network
Overview
What this challenge is about.
You receive 6 months of anonymized O-D trip data (around 4 million trips, around 8,000 virtual stations), the current 9 hand-drawn zones, and the operations team's KPIs (rebalancing trips per day, scooter utilization per zone). Construct a weighted O-D graph and run spectral clustering using the normalized graph Laplacian for K from 8 to 16. Score each K on inter-zone trip share and intra-zone utilization balance. Recommend a K and produce a zone-map GeoJSON the operations team can load into their dispatching dashboard. Write a 2-page memo with a clear before/after comparison.
The Brief
What you'll do, and what you'll demonstrate.
Use spectral clustering on the O-D trip graph to redesign service zones for a shared-mobility fleet and quantify rebalancing-cost savings.
Earning criteria — what you'll demonstrate
- Construct weighted O-D graphs from trip data
- Apply spectral clustering using the graph Laplacian
- Evaluate clustering choices against operational KPIs
- Communicate algorithmic zone redesign to an operations team
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 rolesData Scientist
Applying spectral methods to a real operational graph and delivering a zone map operations can use is exactly the day-one job of a data scientist at any mobility or logistics company.
This challenge sharpens
- spectral-methods
- spectral-clustering
- evaluation
Applied AI Scientist
Translating algorithmic clustering into an operations-ready GeoJSON deliverable is core applied-AI-scientist work in mobility analytics.
This challenge sharpens
- spectral-clustering
- graph-construction
- graph-laplacian
Data Engineer
Building reproducible graph-construction + geospatial pipelines transfers to data-engineering roles on any urban-mobility data team.
This challenge sharpens
- graph-construction
- python
- graph-laplacian