Data Stories
Interactive ML Explorations
Real public datasets. Real machine learning. Creative, non-obvious ways to see the world.
Hospital Quality Survival Landscape
Is your ZIP code your destiny?
Clustering 4,700+ hospitals by 150 quality measures, overlaid with socioeconomic data. UMAP dimensionality reduction, random forest with SHAP interpretation reveal which communities are served by underperforming hospitals.
ML Techniques
- K-Means Clustering
- Random Forest + SHAP
- PCA / UMAP
Visualizations
- Ridge Plots
- UMAP Scatter
- Feature Importance
The Wage Topology
800 occupations. 120 skill dimensions. One landscape.
UMAP dimensionality reduction transforms O*NET skill profiles into an interactive scatter where clusters reveal occupation families, skill-to-wage relationships, and labor market structure.
ML Techniques
- UMAP Embedding
- K-Means Clustering
- Ridge Regression
Visualizations
- UMAP Scatter
- Ridge Plots
- Feature Importance
The Anatomy of $700 Billion
Who actually gets the money?
Network analysis of federal contract and grant spending reveals hidden ecosystems of contractors, geographic dependencies, and structural patterns invisible in aggregate statistics.
ML Techniques
- Louvain Community Detection
- Isolation Forest Anomaly Detection
Visualizations
- Force-Directed Graph
- Bar Charts
- Anomaly Table