Not supported · Patterns · before 2026-09-26 (committed 2026-09-30); timeframe gap fill 2026-10-11
Does removing the Standard Crab improve the hand-picked list?
What this means
Turning off the Standard Crab on the 80-stock list lowered the median profit (+82% vs +95%) and helped on only 26 of 80 stocks. But the comparison baseline comes from a scrape with a confirmed sign bug, the list was picked in-sample, and the settings were not recorded. The numbers should not be relied on; they give no reason to think removing Crab helps. On the full universe, Standard Crab is neither better nor worse than the other patterns on any timeframe, so removing it would not be expected to matter.
The explanation is our best reading; the data shows the result but not the cause directly.
By timeframe
| Timeframe | Verdict | n | Result |
|---|---|---|---|
| 15-minute | Not supported | no pattern differs (best q=0.276) | |
| 1-hour | Not supported | 336 | Crab -0.03R vs rest (-0.17, +0.11), q=0.80 gap fill G8, 2026-10-11 (trade logs) |
| 4-hour | Not supported | 98 | Crab +0.08R vs rest (-0.19, +0.34), q=0.74 gap fill G8, 2026-10-11 (trade logs) |
| Daily | Not supported | 28 | Crab -0.07R vs rest (-0.55, +0.43), q=0.87 gap fill G8, 2026-10-11 (trade logs) |
- Hypothesis
- Turning off Standard Crab raises results on the 80-ticker 'HarmonicList'.
- Method
- TradingView headline scrapes; 80 tickers chosen by PnL >= 60% and win >= 45% in an earlier universe sweep; compared with that sweep's figures for the same tickers. Timeframe not recorded.
- Result
- With Crab: 4,658 tranche trades, 55.6% win, median PnL +94.8%. Without Crab: 4,518 trades, 54.1% win, median +82.3%. No-Crab better on 26 of 80. Gap fill on the universe logs (2026-10-11): Crab vs all other patterns 1h -0.03R (q = 0.80), 4h +0.08R (q = 0.74), daily -0.07R (q = 0.87; 28 setups).
- How much to trust it
- Low: baseline comes from a scrape with a PnL sign bug; in-sample list; settings unrecorded
- Did it change the live rule?
- Crab still enabled
Scripts and data for this study will be linked here when the research code is published on GitHub.
Education and research only. Not financial advice. Backtests use today's index members (survivorship bias).