AI-powered stock analysis & quantitative research
Machine learning models, backtesting frameworks, and data-driven trading strategies — from research to deployment.
Fractional Differentiation in Python: Keep Memory, Get Stationarity
Fixed-width-window fractional differencing in numpy, with a min-d ADF sweep and measured memory-versus-stationarity tradeoffs on a reproducible seeded series.
Fama-French Factor Regression in Python: OLS Without the Unit and Vintage Traps
Run a Fama-French factor regression in Python with statsmodels: excess returns, percent-unit factors, the intercept, and why FIZ and CIZ data must not be mixed.
October 2026 Sentiment & Flow: The Put/Call Divergence Into Q3 Earnings
Equity options lean bullish while index options lean defensive heading into Q3 earnings. Here is how to read the put/call divergence and measure it yourself.
Optimizing an AI-Silicon Portfolio: Markowitz Mean-Variance with pypfopt, Done Right
Mean-variance optimization on NVDA, AMD, AVGO, TSM, ASML, MU, INTC, QCOM, TXN and ARM with pypfopt — Ledoit-Wolf shrinkage, weight bounds and L2 regularization, and when to reach for HRP, Black-Litterman or CVaR instead.
Quant & AI Markets News Roundup: Oct 4, 2026 — Agentic Retail Scales as Institutional Quant Adapts
Robinhood's embedded trading agents, the Fed's first hike since 2023, a new SEC crypto-custody proposal and a September hedge-fund split define this week in quant and AI.
PyBroker Review 2026: ML-Native Backtesting in Python
PyBroker 2.0 folds ML training, walk-forward evaluation and bootstrap metrics into one Python engine, but its Commons Clause licence limits commercial use.
Triple-Barrier Labeling and Meta-Labeling in Python: A 2026 Implementation Guide
A practical Python guide to path-aware trade labels, secondary prediction filters, overlap controls, and reproducible evaluation for quantitative research.