Model a City Bike-Share Network as a Graph for Rebalancing
Overview
What this challenge is about.
Build a directed weighted graph with stations as nodes and edges as aggregated trip volume over rolling windows. Compute (a) betweenness centrality to find high-traffic stations, (b) shortest paths under truck-rebalancing time constraints, and (c) strongly connected components to detect drift in one-way bike flow. Run on 90 days of provided trip data (around 1.9M trips). Visualize the graph on the city map and present 3 operational recommendations (e.g. swap 4 stations between night truck routes) backed by graph metrics. Deliver a notebook, a 7-page recommendation memo, and an in-person presentation to the rebalancing team.
The Brief
What you'll do, and what you'll demonstrate.
Model a 320-station bike-share network as a directed weighted graph and produce 3 operational rebalancing recommendations backed by graph metrics.
Earning criteria — what you'll demonstrate
- Model a real-world transit network as a directed weighted graph
- Apply centrality, shortest path, and SCC analyses correctly
- Visualize graphs on geospatial maps for non-technical audiences
- Translate graph metrics into operational recommendations
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.
Product Manager
Transit-product PMs who can read graph analyses make operational decisions without waiting for a data team to package them.
This challenge sharpens
- data-storytelling
- geospatial-analysis
- centrality-analysis