PARTIAL · real but decaying in-window
Hypothesis
After an impulse leg, the 0.618-0.65 retracement zone is a high-probability continuation entry, the "golden pocket" of fib-based courses.
Definition
\text{zone} = [\,H - 0.65\,(H-L),\; H - 0.618\,(H-L)\,], \qquad \text{impulse } \tfrac{H-L}{L} \ge 6\%
Method
Long the first touch of the zone (setup void on new high or 0.786 break), SL under 0.786, TP at the prior high. Same universe / friction / split. n = 462.
Results
| Trades | 462 |
| Win rate | 39% |
| Mean net per trade | +0.80% |
| Profit factor | 1.57 |
| t-statistic | 2.6 |
| Train / test halves | +1.22% / +0.38% |
| Random-in-uptrend control | −0.18% |
Why it (partially) works
- Strip the fib mysticism and this is buying a pullback inside a fresh impulse trend: a documented momentum effect. The 0.618 level itself is likely incidental; the conditioning on impulse is the substance.
- It beats the random-in-uptrend control by ~1pp/trade, so the timing adds real value beyond trend context.
- But the test half kept only a third of the train edge, consistent with regime sensitivity, thin n, or slow decay.
A real pullback-timing effect hides under the fib branding: +0.80%/trade vs a negative control. Honest caveats: one 84-day window, n=462, and the out-of-sample half is materially weaker. Tradeable edge? Marginal. "Top strategy"? No.
When a retail setup works, it usually works because it accidentally encodes an old academic effect (momentum pullback), not because of the numerology used to sell it.