Data Science · Machine Learning · Quantitative Methods
Turning data into decisions.
I use statistics, machine learning, and causal inference to uncover patterns, build predictive models, and make better decisions under uncertainty.
Selected work
Featured projects
Causal Inference / Policy
Causal Impact of Buy Now, Pay Later
AIPW, IPW, and Causal Forest estimates of BNPL’s effects on debt, late payments, and liquidity using the Survey of Consumer Finances.
Quantitative Finance
Statistical Arbitrage via Pairs Trading
A market-neutral energy-equities strategy achieving a 1.38 Sharpe ratio with 4.2% maximum drawdown after transaction costs.
NLP / LLM
Hallucination-Resistant RAG QA Assistant
Hybrid retrieval and a fine-tuned DeBERTa verification layer that checks cited claims before answers reach users.
From the blog
Recent writing
Article idea
Your Best Customers Might Be the Worst People to Target
Using causal ML to distinguish likely buyers from customers whose decisions a promotion can actually change.
Article idea
My Churn Model Had 90% AUC—and Targeted the Wrong Customers
Why predictive accuracy alone cannot tell you which customers will respond to a retention intervention.