Simulated Annealing for Shift Scheduling at a Hospital
Overview
What this challenge is about.
You receive 6 months of anonymized shift demand data, the nurse roster (skills, certifications, contracted hours), and the labor-law hard constraints. Encode the schedule as a 7-day x 24-shift assignment matrix and implement SA with: a custom neighborhood (swap two nurses on a shift, shift-block move), a temperature schedule, and a soft-violation cost (weekend preference, fairness, consecutive-shift caps). Compare the SA schedule with the current week's hand schedule on hard violations (should be zero), soft violations, and fairness Gini. Write a 2-page memo for nursing management.
The Brief
What you'll do, and what you'll demonstrate.
Build a simulated-annealing nurse scheduler that strictly satisfies labor-law constraints and reduces soft violations vs. the current hand-built schedule.
Earning criteria — what you'll demonstrate
- Implement simulated annealing with a domain-specific neighborhood
- Encode hard vs. soft constraints in a cost function
- Validate optimization output against operational constraints
- Communicate optimization results to non-technical operational leadership
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
Owning an operational optimizer end-to-end, including stakeholder communication with nursing leadership, is exactly the day-one data-science job at any operations-heavy organization.
This challenge sharpens
- scheduling
- optimization
- python
Applied AI Scientist
Encoding a complex constraint structure into a metaheuristic and shipping it as a tool that real operators use is core applied-AI-scientist work.
This challenge sharpens
- simulated-annealing
- constraint-handling
- metaheuristics
AI Product Manager
Defining the right hard/soft constraints and translating stakeholder preferences into a cost function mirrors the AI PM craft of operationalizing fuzzy requirements.
This challenge sharpens
- scheduling
- constraint-handling
- optimization