US Main — Track record
Every elapsed decision is graded against what prices actually did — hit-rates and errors per signal family, plus the cost of the decisions this book chose not to take.
218 graded 3 pending
1W calibration -0.17 How far along the 1-week path a decision typically gets: the fraction of the decided move realized after one week, measured across this book's graded decisions. Feeds a bounded conviction adjustment back into future decisions.
Scorecard
Hit-rates per signal family.
| Signal family | Dir | n | Hit 1W | Hit 4W | Hit 12W | Med err 1W | Stop-first | Bias | Status |
|---|---|---|---|---|---|---|---|---|---|
| NoTrade | sell | 62 | 46% | 55% | 56% | — | 0% | -1 | ● active |
| FailedBreakout_Down_20D | sell | 38 | 57% | 63% | 67% | — | 0% | +1 | ● active |
| PullbackBuy_VWAP | buy | 28 | 46% | 21% | 6% | -3.6% | 46% | -1 | ● active |
| RallySell_BearTrend | sell | 16 | 36% | 30% | 0% | — | 0% | -3 | ● active |
| FailedBreakdown_Up_20D | buy | 15 | 46% | 22% | 0% | -3.4% | 40% | -1 | ● active |
| FailedBreakdown_Up_20D | sell | 14 | 46% | 55% | 100% | — | 0% | -1 | ● active |
| BreakoutUp_52W | buy | 13 | 60% | 11% | 0% | -8.1% | 39% | +2 | ● active |
| BreakoutUp_20D | buy | 7 | 29% | 14% | 17% | -11.3% | 57% | -4 | ● active |
| MomentumContinuation_Up | buy | 6 | 0% | 0% | 17% | -15.4% | 83% | -10 | ● active |
| AnticipationUp_VCP | buy | 5 | 75% | 100% | — | -2.6% | 20% | +5 | ● active |
| AnticipationUp_VCP | sell | 3 | 100% | 100% | — | — | 0% | 0 | ○ building sample (3/5) |
| ? | sell | 2 | 0% | — | — | — | 0% | 0 | ○ building sample (2/5) |
| NoSignal | sell | 2 | 100% | 0% | — | — | 0% | 0 | ○ building sample (2/5) |
| PullbackBuy_VWAP | sell | 2 | 50% | 100% | 100% | — | 0% | 0 | ○ building sample (2/5) |
| BreakdownDown_52W | sell | 1 | 0% | 0% | — | — | 0% | 0 | ○ building sample (1/5) |
| ReversalUp_Oversold | sell | 1 | 0% | — | — | — | 0% | 0 | ○ building sample (1/5) |
| manual_stop_break | sell | 1 | 0% | — | — | — | 0% | 0 | ○ building sample (1/5) |
| muted_no_close | sell | 1 | 0% | — | — | — | 0% | 0 | ○ building sample (1/5) |
| muted_no_scan_row | sell | 1 | 0% | — | — | — | 0% | 0 | ○ building sample (1/5) |
Counterfactuals Counterfactuals grade decisions that were NOT executed — expired queues, no-chase rules, untaken optional trims — against what the market then did. They are kept strictly separate from the calibration cells above.
What the decisions we didn't take would have done.
- No-chase queue (queued a pullback instead of chasing) — 44 cases , median would-have 1W move +0.7% → verdict: cost
- Optional trims not taken — 45 cases , median would-have 1W move +0.2% → verdict: saved
- Anticipate slot (pre-breakout buy-stop) — 14 cases , median would-have 1W move -0.8% → verdict: saved
Counterfactuals are advisory evidence for the book's learnings reviews — never blended into the calibration cells.