Selected Work

Published first-author paper improving ADR prediction via rigorous interpretability (SHAP, feature importance) across Random Forest, Gradient Boosting, and SVM.

Fused LSTM time-series with FinBERT sentiment embeddings to predict AAPL direction and price — beat linear baseline by 15pp accuracy. IEOR 242B team capstone.

Three-month quantitative deep-dive on spot Bitcoin ETFs: decomposed premium/discount dynamics across 12 products and identified a persistent 3–7bp arbitrage window.