Building Alpha with Discipline.
I'm Muhammad Ahmad Mujtaba Mahmood.
MS Quantitative Finance candidate focused on factor modeling, systematic research, and production-grade data engineering for investment workflows.
Selected Work
Quantitative Data Pipeline & Factor Engineering
Built a leakage-aware equity research pipeline with strict time-based data availability checks. Engineered momentum and rolling beta factors and exported a structured HDF5 dataset for robust cross-sectional testing.
Linear PCA vs Deep Autoencoders for Risk Factors
Designed a comparative framework in PyTorch to extract latent risk drivers from S&P 500 returns. The non-linear autoencoder improved reconstruction in calm regimes, while PCA remained more stable in stress regimes for hedging.
Intraday Momentum Strategy on SPY (1-Minute Data)
Implemented an intraday momentum strategy with volatility-targeted sizing and VWAP-aware trailing stops. Backtests on 2008-2020 SPY data achieved 18.2% annualized return with Sharpe above 1.0 under realistic transaction costs.
ASML Equity Research & Scenario Valuation
Co-authored an investment pitch on ASML by combining bottom-up financial analysis with scenario-based valuation. Built revenue sensitivity and policy risk views to quantify upside/downside dispersion under multiple demand environments.
Spotlight
Key milestones, awards, and work highlights.
Junior Analyst - 360 Huntington Fund
Performed fundamental and quantitative analysis on semiconductor equities, and co-authored an investment pitch on ASML with structured valuation and risk scenarios.
Data Engineering - Global Financial Media
Designed Spring Boot and AWS backend systems and automated cross-database synchronization for reliable high-frequency data delivery and analytics.