AMD
Accumulation → Manipulation → Distribution. Asia establishes range, London sweeps one side, NY trades toward the opposite. Tier 1 touch magnet — 65% within 120 min.
updated 2026-04-23The setup
Asia session (20:00–00:00 ET) quietly builds a range. London (02:00–05:00 ET) sweeps one side of that range — typically the side opposite the eventual NY bias. New York then trades toward the other extreme of the London move.
If London sweeps Asia high → bearish manipulation → NY targets London low. If London sweeps Asia low → bullish manipulation → NY targets London high.
The line drawn on our heads-up display (HUD) is the touch target — it marks where NY is expected to visit, not necessarily close past.
Entry rules
- Session: NY (09:30–11:30 ET window)
- Trigger: one side of Asia has been swept during London, the other has not (
ONLY_HorONLY_L) - Direction: opposite the London sweep
- Target: the London extreme that wasn’t swept
- Probability: 65–68 (touch, not close)
- TTL: 120 minutes
The signal gets a time-decay haircut as the window burns:
| Minutes in | Touch-rate multiplier |
|---|---|
| 0–30 | 1.00× (≈65%) |
| 30–60 | 0.40× (≈26%) |
| 60–90 | 0.22× (≈14%) |
| 90–120 | 0.10× (≈6%) |
If it’s going to run, it runs fast. Median touch time is 3–4 minutes.
Backtest
n = 1,013 ONLY_H / ONLY_L sessions (5-year MNQ 1-min):
| Window | Touch rate | % of eventual hits captured |
|---|---|---|
| 30 min | 52.6% | 72% |
| 60 min | 59.1% | 81% |
| 120 min | 64.9% | 89% |
| 180 min | 67.9% | 93% |
| 390 min (full RTH) | 73.1% | 100% |
- Median excursion past target when hit: +102 points (huge follow-through)
- Best DOW: Wed 78% · Worst: Thu 69% · Mon 67% · Fri 76%
- No day-of-week is structurally broken
The re-audit story
An earlier audit looked at AMD as a close-direction predictor — and it failed (47–53%, pure noise). That almost got the whole signal demoted.
But “high probability” was the wrong frame. AMD isn’t a close-direction signal; it’s a touch magnet. Price visits the target at some point during the session, then does whatever it wants. Different question, different answer.
The old 88–92% figure was from a flawed baseline. The 65% at 120 min number above is the correct one, measured against proper conditional-remaining-touch rates.
Full writeup: Touch vs close direction — two questions, two signals (coming soon)
Kill-switch interaction
If both Asia high and low get swept during 02:00–05:00 ET, the day is a chop day (lon_both_swept=True). A −10 probability penalty is applied; lines that drop below prob 40 are removed. AMD is one of the penalized signals.
Regime-conflict penalty (2026-04-23)
A follow-up audit (n=1,105 AMD signals in the backtest CSV) asked the opposite question: does AMD break down when the broader regime points the other way? Base rates are strong — BULL 94.5% (n=582) / BEAR 90.2% (n=523) by the touch-rate metric in the results file — but two conflict axes chew into that:
Gap state (RTH open vs prior day H/L):
| Signal | Gap state | Hit rate | n | Δ vs base |
|---|---|---|---|---|
| AMD BEAR | ABOVE_PDH | 81.7% | 115 | −8% |
| AMD BULL | BELOW_PDL | 81.6% | 87 | −13% |
Gap × 4H trend (the combined cell, not additive):
| Signal | Cell | Hit rate | n | Action |
|---|---|---|---|---|
| AMD BEAR | ABOVE_PDH + 4H BULL | 77.4% | 93 | −13 prob |
| AMD BULL | BELOW_PDL + 4H BEAR | 76.6% | 64 | kill-switch |
The implementation lives in PredictionModel.cs / PredictionModelWeb.cs immediately after the lon_both_swept block, and in backtest_prediction_model.py at the Model 14 consume site. Penalties are non-stacking: the matrix cell is a direct measurement, not a sum of independent effects.
Friday DOW also showed degradation in this audit (BULL 72.7% / BEAR 68.4% vs 91–100% Mon–Thu). The −20 Friday penalty that was removed on 2026-04-22 as a “flawed metric” has been reinstated in both PredictionModel.cs / PredictionModelWeb.cs and remains in backtest_prediction_model.py — the touch-rate measurement shows the DOW effect is real.
Full audit: C:\SMC\backtest_results\amd_regime_audit.txt.
Why Tier 1
Even at 65% touch with aggressive time decay, this is one of the highest-confidence lines on the board. The touch edge is stable across DOW, years, and regime. The “magnet” nature means it’s an honest touch signal even when the market has no directional conviction.
History
- 2026-04-18 — Target + probability fix.
- 2026-04-19 — Confluence tuning, Friday penalty applied.
- 2026-04-21 — Temporarily demoted to Tier 2 over close-direction audit.
- 2026-04-22 — Re-audit, Tier 1 restored, probabilities recalibrated to touch-rate reality, Friday penalty removed, TTL tightened 270→120 min.
- 2026-04-23 —
lon_both_sweptkill-switch applied. - 2026-04-23 — Regime-conflict penalty added: gap_state × 4H trend matrix; BULL+BELOW_PDL+4H BEAR is a hard kill-switch (76.6%, n=64).
- 2026-04-23 — Friday −20 penalty reinstated in live indicator to match backtest (Fri BULL 72.7% / BEAR 68.4% vs Mon–Thu 91–100%).