UN x DATABRICKS CHALLENGE:
Description: This is a Geo-Insight Challenge. Which Crises Are Most Overlooked? Using publicly available crisis severity and funding data, create a map showing mismatches between humanitarian needs and Pooled Fund coverage. Use project-level data (budgets, cluster, population indicators) to flag unusually high or low beneficiary-to-budget ratios and suggest comparable projects for benchmarking.
Starting Datasets (not required or limited to these)
All projects will be shared directly with the teams at the UN working on this exact problem. Judges include representatives from the UN and Databricks.
Using publicly available crisis severity and funding data- show mismatches between humanitarian needs and Pooled Fund coverage → Bioinformatics at a large scale→ health biology
Which regions need the most care and funds → where should resources go to first? How much more do they need?
Better public health interventions → Health Technology because it tells them where to go first through technology
AI System that predicts where humanitarian health crises will be most underfunded + medically vulnerable next → based off of health indicators + funding data
Streamlit- Rapid Prototyping +_ Demonstrations
pandas, matplotlib, plotly, scikit-learn