sp100

S&P100 stocks analysis via Graph Neural Networks (Forecasting, Clustering, Trend classification, Stocks ranking for optimal stock picking)

Project for the Quantitative Finance PhD course at Scuola Normale Superiore (SNS): MATLAB empirical backtesting, code, and slides demonstrating the out-of-sample limitations of Marcos López de Prado's paper "Building Diversified Portfolios that Outperform Out-of-Sample".

Quantifying the impact of the Russia-Ukraine War on S&P 100 equities using Event Study Methodology (ESM). Analyzes Cumulative Abnormal Returns (CAR) across 3 conflict milestones to measure how Tier-1 regional supply chain dependencies and corporate ESG disclosure scores drive market resilience and shock absorption.

Walk-forward portfolio backtesting using TimesFM 2.5 quantile forecasting across US (S&P 100) and India (Nifty 50) equity markets. Uncertainty bands drive a mean-variance optimizer with return-shrinkage penalty.