How to use AlphaScreen

Protocol: 7 randomly-seeded ~5-month windows (Jan–Jul 2026), $17k across 5 slots, next-open entries, OTOCO brackets (−8% stop / +35% target), 15-day max hold, market-regime gate on entries. Sprints re-run until today. Educational research, not advice.

*Seven windows compounded (overlapping — treat as illustrative, not a CAGR). †Mean/σ of window returns, √7-scaled; benchmarks score higher per unit of volatility because index returns are steadier — the engines earn ~4× more per window at ~2× the dispersion.

How the signals stemmed losses: win rates near 33–38% would lose money with symmetric exits — the whole edge is exit asymmetry. The −8% OTOCO stop caps every loser while the +35% target and 15-day time-exit let winners average +2.8–2.9%/trade; in the April drawdown windows the regime gate (SPY<EMA23 → no new entries) kept fresh capital out while SPY fell −5%, cutting engine drawdowns to −11/−14% on portfolios 4× more aggressive than the index. The same discipline costs a little in V-shaped recoveries (gate re-opens one weekly check late) — the accepted price of the shield.

Recommended changes (from this study): keep the 3-week sprint limit (removing it costs ~10pp/window); prefer HMM's entry gate in choppy tapes (higher win rate, lowest DD); a hybrid — RS ranking gated by HMM ENTER — is the top candidate for improving Sharpe toward index-level steadiness.

RS (Relative Strength)

1–99 percentile rank of a stock's price performance vs the S&P 500 across the last year (recent quarters weighted heavier). 99 = outperformed nearly everything.

RMV (Relative Measured Volatility)

How tight the recent price range is. Low RMV = volatility contraction (a coiling base) — the setup shape that precedes many breakouts.

RRG (Relative Rotation Graph)

A map of sectors/stocks rotating through Leading → Weakening → Lagging → Improving quadrants vs the benchmark.

Sprint

A time-boxed (3-week) basket of the highest-RS setups. Backtests show the time limit itself adds return — capital never sits in stalled names.

HMM (Hidden Markov Model)

A statistical engine that estimates the probability a stock is entering an "explosive" state; it opens up to 5 positions when strict entry gates pass.

DCR

Daily Closing Range — where price closed within the day's range (100 = at the high). Persistent high DCR signals accumulation.

Market Gate / Master Banner

A go/no-go switch computed from SPY trend + volatility. When closed, engines stop opening new positions.

MPT Barbell

An ETF portfolio mixing low-beta hedges + a core + high-beta growth, rebalanced by rules — diversification with a momentum engine.

Extension (ext50)

% distance above the 50-day average. Too extended = late entry; engines penalize it.

Stage Analysis

Weinstein's 4 stages (basing, advancing, topping, declining). We want Stage 2 advances.