What are we busy about?
summary
Automated scheduling pipeline uses CP-SAT via OR-Tools with Pandas and NumPy to encode availability, state medical licenses and labor constraints, then emits shift assignments into the backend and data warehouse. The model optimizes for prioritized full‑timers and minimum‑available doctors, enforces max‑8h shifts and nurse ratios, and runs for 100+ doctors at Antidote Health, cutting manual errors, stabilizing coverage and increasing doctor productivity and patient scheduling consistency.
AI-written summary · about
chapters (6)
- 0:00Introduction and speaker intro
- 1:59About Antidote Health
- 2:40Optimization problems we solve
- 8:16Introducing OR-Tools
- 15:36Benefits of automating scheduling
- 17:03Acknowledgments and closing
related talks
19mLeveraging Analytics for Technical Efficiency and Enhanced User Experience
16mPractically predictable – Forecasting delivery when nothing is certai
30mAI-based Assistant for Business Process Outsourcing
17mWe can automate that!
44mThe Math behind Project Scheduling, Bug Tracking, and Triage
31mAn incomplete list of implementing data science effectively
22mHow we improved our monitoring so that everyone likes to be on-call
12mUse ML to Predict Delivery Time and Improve Code Reliability