Methodology
Complete transparency into the V11 pipeline. Every step documented, every assumption stated, every result out-of-sample.
Pipeline Overview
Universe & Data Collection
46 US mega-cap equities from the S&P 100, filtered for options liquidity (500+ contracts daily OI). Price, volume, and fundamental data sourced from standard market data providers with daily reconciliation.
Factor Construction
Nine cross-sectional factors computed per stock. Each undergoes IC testing; factors with |IC| < 0.01 are pruned. Remaining factors are winsorized at 5th/95th percentiles and z-score normalized.
Adaptive Ensemble
Ridge, ElasticNet, and Gradient Boosting trained on the factor matrix. Weights determined by inverse OOS MAE with regime adjustment. James-Stein shrinkage applied to blended predictions.
Monte Carlo & Vol Surface
80,000-path GBM simulation per stock. Model-implied vol compared against market ATM IV to compute the volatility edge metric.
Options Strategy Selection
Five strategies evaluated per stock (stock, ATM call, OTM Δ20 call, bull call spread, put credit spread). Re-priced with the evidence-based spread model (R² = 0.405). Selection follows conviction × vol-edge matrix.
Portfolio Construction
Drawdown-adjusted Kelly sizing. Intra-sector diversification constraints. Options allocation capped at 30% (HIGH) and 15% (MED).
Factor Definitions
| # | Factor | Description |
|---|---|---|
| 1 | Momentum (12-1) | Trailing 12-month return excluding the most recent month |
| 2 | Short-Term Reversal | 1-month lagged return capturing mean-reversion |
| 3 | Earnings Surprise | Latest quarterly EPS surprise as % of consensus |
| 4 | ROE Change | Year-over-year change in return on equity |
| 5 | Analyst Revision | Net 90-day EPS estimate revisions normalized by price |
| 6 | Volatility Ratio | 30d / 90d realized volatility ratio |
| 7 | Volume Trend | 20-day volume SMA relative to 60-day baseline |
| 8 | Beta Residual | CAPM beta-adjusted residual return |
| 9 | IV Percentile | 30-day IV percentile rank over 252 trading days |
Ensemble Architecture
L2-regularized linear baseline. Stable, low variance. Dominates in low-vol regimes.
L1+L2 for automatic feature selection. Identifies predictive factor subsets.
Non-linear tree ensemble. Captures factor interactions. Elevated in high-VIX.
Evidence-Based Spread Model
Specification
Key Finding
Bid-ask spreads vary dramatically across tickers and moneyness. OTM options on lower-liquidity names can have spreads exceeding 15% of premium, making apparently profitable strategies deeply unprofitable after execution costs.
Conviction × Vol-Edge Matrix
| Tier | Criteria | Vol Cheap | Vol Rich |
|---|---|---|---|
| HIGH | Pred > 30%, EC > 85% | OTM Call (Δ20) | ATM Call |
| MED | Pred 15–30%, EC 65–85% | ATM Call | Put Credit |
| LOW | Pred < 15% or EC < 65% | Stock only | Stock only |
This methodology document describes quantitative research techniques. Not investment advice.