Negative after costs

1000PEPEUSDT · 60m · Verdict Card

Percentile-deviation fade (mean reversion) · mr_percentile · hold 24 · 2025-06-01 → 2026-10-11 · 11929 bars · bybit · 2026-10-12 12:49

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 + 0.12bp/bar funding

Trades

149

Win rate

53.0%

Avg / trade

-36bp

Gross avg

-16bp

Total

-5324bp

t-stat

-0.72

Permutation p

0.6262 · T0.616/S0.626

95% CI of mean

[-131bp, 64bp]

Max drawdown

63.1%

Exposure

36.0%

Profit factor

0.84

Worst trade

-3277bp

Median

43bp

Equity curve (log)

Buy & hold: -65.7% · 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 → 2025-12-04	38	-102bp	42%	-1.22
Seg 2	2025-12-05 → 2026-03-08	38	-52bp	55%	-0.42
Seg 3	2026-03-11 → 2026-07-08	38	15bp	55%	0.22
Seg 4	2026-07-10 → 2026-10-08	35	-2bp	60%	-0.01

In-sample/Out-of-sample	Trades	Avg / trade	Win rate	t-stat
In-sample 60%	89	-45bp	52%	-0.68
Out-of-sample	60	-22bp	55%	-0.29

Trade log · last 12 trades

Time	Side	Entry px	Exit px	Bars held	Exit	Net
2026-10-08 23:00	LONG	0.003745	0.003893	24	time	367.7bp
2026-10-07 12:00	LONG	0.004091	0.00403	24	time	-170.1bp
2026-10-05 16:00	SHORT	0.004521	0.004347	24	time	372.6bp
2026-10-03 13:00	LONG	0.004243	0.004277	24	time	59.9bp
2026-10-02 12:00	SHORT	0.004679	0.004235	24	time	977.1bp
2026-09-28 14:00	LONG	0.00416	0.004213	24	time	106.7bp
2026-09-25 17:00	SHORT	0.004485	0.004391	24	time	191.9bp
2026-09-24 12:00	LONG	0.004409	0.004418	24	time	0.5bp
2026-09-23 11:00	LONG	0.004959	0.00436	24	time	-1307.2bp
2026-09-22 03:00	SHORT	0.004969	0.004888	24	time	144.5bp
2026-09-21 02:00	LONG	0.003993	0.004994	24	time	2217.1bp
2026-09-20 00:00	SHORT	0.004048	0.004023	24	time	42.1bp

Method & known limits

Exit: fixed 24-bar hold; fill=signal bar close
Costs: 5.5bp/side fee + 3bp/side slippage + 0.12bp/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=0.6157; (2) sign-flip permutation: each trade's realized move kept, direction re-rolled (variance-matched, stricter for fades), p=0.6262. Verdict uses the stricter p=0.6262 (2000 trials, seed 42, reproducible)
The null must match the live procedure trade-for-trade: every surrogate fills the same count (149 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 [-131bp, 64bp] — 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.