Negative after costs

ETHUSDT · 60m · Verdict Card

Percentile-deviation fade (mean reversion) · mr_percentile · hold 24 · 2025-06-01 → 2026-10-11 · 11929 bars · bybit · 2026-10-12 12:48

Rule: Fade when the 24-bar log deviation |d| ≥ its rolling p80 percentile (threshold recomputed every 168 bars); long & short
Cost model: 5.5bp/side fee + 3bp/side slippage + 0.06bp/bar funding

Trades

138

Win rate

50.0%

Avg / trade

-52bp

Gross avg

-33bp

Total

-7165bp

t-stat

-1.85

Permutation p

0.8831 · T0.883/S0.880

95% CI of mean

[-105bp, 4bp]

Max drawdown

55.8%

Exposure

33.4%

Profit factor

0.65

Worst trade

-1198bp

Median

11bp

Equity curve (log)

Buy & hold: -0.9% · missing 0 (max gap 0) · OHLC complete

Stability by segment

Seg	From → To	Trades	Avg / trade	Win rate	t-stat
Seg 1	2025-08-23 → 2025-11-14	35	-18bp	51%	-0.36
Seg 2	2025-11-17 → 2026-02-08	35	-99bp	46%	-1.76
Seg 3	2026-02-09 → 2026-05-23	35	6bp	60%	0.11
Seg 4	2026-05-24 → 2026-10-08	33	-99bp	42%	-1.65

In-sample/Out-of-sample	Trades	Avg / trade	Win rate	t-stat
In-sample 60%	82	-61bp	48%	-1.68
Out-of-sample	56	-39bp	54%	-0.87

Trade log · last 12 trades

Time	Side	Entry px	Exit px	Bars held	Exit	Net
2026-10-08 23:00	LONG	2434.19	2487.51	24	time	198.2bp
2026-10-07 16:00	LONG	2607.96	2558.49	24	time	-210bp
2026-09-21 16:00	SHORT	2695.39	2747.48	24	time	-209.9bp
2026-09-18 22:00	SHORT	2581.8	2637.44	24	time	-231.7bp
2026-09-16 00:00	LONG	2421.08	2390.67	24	time	-144.8bp
2026-09-11 21:00	SHORT	2629.27	2543.6	24	time	312.8bp
2026-09-10 20:00	LONG	2413.08	2510.39	24	time	376.9bp
2026-09-03 22:00	SHORT	2488.56	2438.81	24	time	183.5bp
2026-08-23 05:00	LONG	2406.68	2469.14	24	time	237.8bp
2026-08-22 02:00	SHORT	2419.76	2426.78	24	time	-47.4bp
2026-08-21 00:00	SHORT	2343.98	2405.35	24	time	-276.9bp
2026-08-19 23:00	SHORT	2084.94	2325.01	24	time	-1108.3bp

Method & known limits

Exit: fixed 24-bar hold; fill=signal bar close
Costs: 5.5bp/side fee + 3bp/side slippage + 0.06bp/bar funding drag (same both sides; funding sign not modeled)
Non-overlapping: signals during open positions are dropped
Significance: t-stat on per-trade net returns. Two nulls — (1) timing permutation: entry times randomized, direction mix kept, same trade count, same non-overlap suppression, p=0.8831; (2) sign-flip permutation: each trade's realized move kept, direction re-rolled (variance-matched, stricter for fades), p=0.8796. Verdict uses the stricter p=0.8831 (2000 trials, seed 42, reproducible)
The null must match the live procedure trade-for-trade: every surrogate fills the same count (138 entries, 2000 effective trials). A surrogate that only fills ~9 entries widens the null about 4x and can fake p=0.30 out of p=0.01
Uncertainty: mean 95% bootstrap CI [-105bp, 4bp] — spanning 0 means no claim of edge
Sample: 11929 bars of 60m, 0 missing (max gap 0), OHLC complete
Splits: first 60% in-sample, rest out-of-sample, plus 4 time blocks to catch single-segment flukes
Params: k=24 pct=80 side=both warmup=2000 rebalance=168 — if tuned on this same history the verdict carries selection bias; collect out-of-sample before believing it
Known limits: no order-book depth so slippage is assumed; liquidation/margin/liquidity not modeled; rejected or partial fills not modeled
Null sensitivity: the sign-flip test keeps each trade's realized move and re-rolls only the direction, so the long/short allocation itself counts as evidence — in a one-way market that can inflate significance. Hence the verdict requires both nulls to clear, a positive net mean and a positive out-of-sample mean; miss one and it degrades to "not separated from luck"

This card only judges whether a rule has statistical evidence under stated costs. Not investment advice; past results do not predict future returns.