Mawandu/ml-healthcare-access-africa

Machine Learning analysis of healthcare accessibility in Sub-Saharan Africa. Geospatial clustering, predictive modeling, and optimization recommendations using 98K+ health facilities data from UN/HDX. # ML Healthcare Access Africa 🏥🌍 > Machine Learning analysis of healthcare facility distribution and accessibility in Sub-Saharan Africa using geospatial data and clustering algorithms. ## 🎯 Objective Optimize healthcare infrastructure placement and identify underserved regions using ML techniques on 98,745+ health facilities across Sub-Saharan Africa. ## 🔧 Tech Stack - **Geospatial**: GeoPandas, Folium, Shapely - **ML**: Scikit-learn, K-means clustering, Random Forest - **Visualization**: Plotly, Matplotlib, Seaborn - **Data**: HDX/UN Health Facilities Dataset ## 📊 Key Features - Interactive mapping of health facilities - Geospatial clustering analysis - Accessibility gap identification - Predictive modeling for optimal placement - Policy recommendations generator