AI & Data Researcher
THRC, Texas State University
Jan 2025 – Present
- Engineered multi-source data integration pipeline merging five years of CDC BRFSS SMART survey data (2015–2019) with MSA-level Distress Community Index (DCI) spatial statistics, producing a master dataset for population health analysis.
- Implemented spatial analytics (Global/Local Moran's I via PySAL, KNN spatial weights k=6, spatial Gini coefficient) and authored structured methodological documentation for data pipeline reproducibility.
- Developed MSA-level aggregation and LISA cluster classification (HH/LL/HL/LH) with population-weighted shares, enabling identification of geographic health disparity patterns across U.S. metro areas.