Greater Philadelphia
Experienced quantitative researcher specialising in mid-frequency systematic equities, with a focus on ML-based alpha signal construction, factor modelling, and portfolio optimisation. Currently pursuing a Master's at The Wharton School (Quantitative Finance & Statistics) and interned at QSentia, an AI-driven systematic hedge fund. At QSentia, I conducted hypothesis testing and alpha research on implied volatility term structures to develop predictive features for cross-sectional downside risk prediction. Previously, at J.P. Morgan, I built and deployed systematic indices, market-impact-controlled rebalance models, and sentiment-based strategies across multi-billion-dollar mandates. Interested in opportunities within quantitative research, alpha discovery, and systematic strategy development across equities and multi-asset domains.
• Hypothesized and tested vol-based downside-risk signal to capture short-term equity drawdowns; observed predictive strength concentrated in highest signal decile and confirmed signal stability across regimes using rolling IC analysis • Reduced drawdown by 20% in a Reinforcement Learning-based long-only U.S. equity strategy by applying partial least squares (PLS) regression to the implied-volatility term structure, enabling prediction of downside risk
• Built equity risk premia strategies using Barra factors; applied convex optimisation (MOSEK) to construct market-neutral indices maximizing target factor exposure; researched factor IC persistence to determine optimal rebalance frequency for 20+ indices • Engineered “Multiday Rebalance” framework to mitigate market-impact of mega-volume trades on sector indices; leveraged Almgren-Chriss model to optimize rebalance schedule; backtested and launched 39 indices generating $XX M revenue • Boosted merger-arbitrage strategy Sharpe by 50% by alpha research on option chain data; applied logistic regression on target IV surface to infer deal completion probability; drafted index rules and productionised new strategy attracting $X B notional • Developed NLP-driven thematic strategies using Ravenpack news analytics data; scored equities based on theme relevance and sentiment to optimize portfolio; launched 10 themes generating $X M in annual revenue • Created indicative pricing solution for exotic barriers using Monte Carlo, enabling real-time quotes for $XXX M notional trades • Conducted root-cause analysis on index reconciliation breaks across option indices, equity risk premia, merger arbitrage NLP-based thematic strategies; implemented fixes stabilizing production workflows for 1k+ indices