Strategy research · open notebook

A public corpus of /ES strategies, tested and graded.

Every strategy idea — generated, variation-swept, and tested against 12 months of CME tick data — lives in this corpus. Walk-forward validation, regime decomposition, full kill log. The survival rate is intentionally low; only the strategies that clear the bar are promoted to production.

Updated Tested Survival
Tested
strategies
Promoted
grade A/B
Killed
grade F
Best PF
in corpus
Best μ
pts/trade
Kill rate
of graded
Method

Three filters every strategy clears (or fails).

A strategy is just a hypothesis until it survives all three. Most don't. That's the point.

01 · IN-SAMPLE

Full-period backtest

Run against 12 months of 1-min CME data. Compute PF, win rate, mean edge, max drawdown. PF floor: 1.2. Sample size floor: 30 signals.

02 · OUT-OF-SAMPLE

Walk-forward replay

Train on the first window, test on a held-out trailing window. If OOS PF doesn't hold within 20% of full-period PF, the strategy is killed regardless of in-sample edge.

03 · REGIME DECOMP

VIX + day-type breakdown

Performance is decomposed across vol regimes (low/normal/high) and day types (trend / balance / reversal). A strategy that only works in one regime gets flagged for conditional production.

The corpus

What's in there.

A read of the corpus shape: outcome by grade, category mix, and edge distribution among profitable strategies.

Outcome by grade

Distribution of grades across all completed tests.

Category mix

Strategy ideas tested, grouped by their category tag.

Mean edge distribution (profitable strategies only)

Among strategies that closed profitable in-sample, where the per-trade edge landed. Green ≥ 3pts (meaningful), gray below.
Recent tests

The last twenty strategies the lab evaluated.

Every row is a hypothesis we tested and graded.

Date Name Category Grade N WR PF
Loading manifest…
Go deeper

Specialized views.

Different cuts on the same corpus.