Epidemic Demand Forecasting for Regional Healthcare

Problem

A regional healthcare system in a developing market lacked reliable case forecasting to plan ICU capacity, oxygen supply, and public-health interventions. Off-the-shelf global models did not generalise to local epidemiological data.

Approach

Led the machine-learning track in a globally distributed team of 15+ contributors. Implemented XGBoost time-series models with feature engineering on public-health data, and built an interactive dashboard for non-technical stakeholders to explore forecasts.

Result

Regional health planners now forecast ICU demand 4 weeks ahead with 28% better accuracy than their previous baseline.

• ◆28% more accurate forecasts than the previous method
• ◆Planners make data-backed ICU capacity decisions 4 weeks ahead
• ◆Non-technical staff explore forecasts without asking data teams
• ◆Oxygen supply and staffing planned proactively, not reactively