MS Financial Economics · Columbia Business School
Portfolio management · Quantitative finance
I’m currently an MS Financial Economics student at Columbia Business School, after completing my BSc in Economics, Management and Computer Science at Bocconi University. I’m interested in portfolio management and quantitative finance, especially how machine learning and statistical methods can help us understand markets, find persistent sources of alpha, and develop practical investment strategies. My current focus is on equity selection, portfolio construction, and testing ideas with point-in-time data, realistic costs, and disciplined risk controls.
A point-in-time study of U.S. equities using market, fundamental, analyst, options, filing, and news data—built around realistic portfolio constraints and transaction costs.
A LightGBM allocation study combining macroeconomic and technical signals with walk-forward and bootstrap testing.
Cross-sector momentum with monthly rebalancing and explicit analysis of drawdown and market sensitivity.
Applied Random Forest, XGBoost, and LightGBM to genomic data to predict Oncotype risk scores, achieving 0.87 AUC and validating model behavior with SHAP and LIME.
Built Python alternative-data pipelines, launched RoketAI, and converted recurring data requests into automated generative-AI workflows.
Evaluated technology companies using DCF, comparable-company analysis, operating benchmarks, and commercial research; supported the Toptan pilot.
Developed trading and risk models for commodity-backed digital assets, automated market-data pipelines, and produced systematic forecasts.
Financial econometrics, capital markets, market microstructure, big data in finance, and empirical asset pricing.
GMAT 735 · Quantitative 100th percentile
Economics, statistics, machine learning, programming, databases, and portfolio management.
Merit Scholarship