I apply applied econometrics and data science to investigate agricultural finance, resource economics, and spatial markets. I utilize Python and spatial datasets to evaluate crop yields, rural credit risk, and land use dynamics.
My goal is to bridge the gap between technical data science and applied economics, utilizing methods like Fixed-Effects Panel Regressions, Spatial Data Integration, and Causal Inference to evaluate resource allocation and economic policy.
🎯 Open to research collaborations and academic opportunities.
How Do Automated Decision Systems Penalize Marginalized Groups, & Can We Fix It Without Breaking The Model?
Auditing a fintech credit scoring model for gender bias using Python and Fairlearn. Investigating FAccT principles in information systems. I replicated a credit scoring pipeline and applied Microsoft’s Fairlearn toolkit to test ‘Demographic Parity’ constraints.
Panel Data Analysis of Climate Variances on Regional Crop Yields A Computational Social Science project utilizing Python, FCC reverse-geocoding APIs, and Two-Way Fixed-Effects regression to empirically isolate the causal impact of temperature variances on US agricultural outputs.
Social Media Sentiment & Topic Extraction
A Computational Text Analysis project using Python, VADER, and Gensim. Built an automated pipeline to clean unstructured social media comments, quantify public sentiment, and extract latent discourse topics using Latent Dirichlet Allocation (LDA). This text-processing pipeline can be adapted to scrape and analyze unstructured economic policy documents, agricultural news sentiment, or commodity market reports.
The Airbnb Effect: NYC Housing Markets
A Computational Social Science project using Python and OLS Regression to quantify how short-term rental density impacts local housing prices across 164 NYC neighborhoods.