Peer-review-ready quantitative research. Every model is backtested out-of-sample with full methodology disclosed. Papers are time-stamped before evaluation.
A 9-factor adaptive ensemble combining Ridge, ElasticNet, and Gradient Boosting with James-Stein shrinkage and VIX regime detection. Out-of-sample IC of 0.042 across 46 mega-cap equities with stable performance across regime transitions.
A Ridge regression model trained on 282 real options chain observations predicting per-ticker, per-moneyness execution costs. Incorporating spread drag eliminates 14 of 46 apparently profitable strategies that would otherwise destroy alpha.
Drawdown-adjusted Kelly sizing with conviction tiers. HIGH conviction stocks receive call options for convexity; MED conviction uses put credits when implied vol exceeds realized. Framework produces consistent tier-ordered returns.
Model-implied volatility from GBM simulation compared against market ATM IV. The vol-edge metric identifies systematic mispricings that inform strategy selection across the conviction tiers.
Sector Momentum Decomposition and Factor Timing Signals
Q2 2026Earnings Surprise Integration with Fundamental Factor Models
Q2 2026Cross-Asset Regime Classification Using Credit Spreads and Yield Curves
Q3 2026All predictions are time-stamped and published before the out-of-sample evaluation period begins.
Full pipeline parameters, data sources, and model specifications are documented for independent replication.
Every backtest includes evidence-based execution costs from real options chain observations. No frictionless assumptions.