Negative after costs

BTCUSDT · 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

195

Win rate

46.2%

Avg / trade

-32bp

Gross avg

-14bp

Total

-6304bp

t-stat

-1.99

Permutation p

0.8031 · T0.803/S0.800

95% CI of mean

[-63bp, -2bp]

Max drawdown

50.6%

Exposure

47.1%

Profit factor

0.68

Worst trade

-992bp

Median

-18bp

Equity curve (log)

Buy & hold: -20.6% · 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	49	-45bp	49%	-1.56
Seg 2	2025-11-18 → 2026-02-13	49	-13bp	49%	-0.33
Seg 3	2026-02-14 → 2026-05-27	49	-22bp	47%	-0.76
Seg 4	2026-05-28 → 2026-10-08	48	-49bp	40%	-1.66

In-sample/Out-of-sample	Trades	Avg / trade	Win rate	t-stat
In-sample 60%	117	-29bp	49%	-1.27
Out-of-sample	78	-38bp	42%	-1.70

Trade log · last 12 trades

Time	Side	Entry px	Exit px	Bars held	Exit	Net
2026-10-08 23:00	LONG	80986.8	82837.9	24	time	207.6bp
2026-10-07 16:00	LONG	83907.6	82835.1	24	time	-147.1bp
2026-10-02 12:00	SHORT	86626.8	84537.3	24	time	225.7bp
2026-09-28 17:00	LONG	82645.4	84226.1	24	time	171bp
2026-09-23 23:00	LONG	83957	84379.8	24	time	31.8bp
2026-09-21 16:00	SHORT	83724.2	86171.4	24	time	-306.5bp
2026-09-19 19:00	SHORT	81281.1	80443	24	time	85.2bp
2026-09-18 18:00	SHORT	78254.6	81204.6	24	time	-388.5bp
2026-09-15 22:00	LONG	75906.5	75665	24	time	-50.3bp
2026-09-11 21:00	SHORT	79213	77335.8	24	time	221.4bp
2026-09-10 20:00	LONG	76867.9	77989.5	24	time	126.4bp
2026-09-05 03:00	LONG	79738.6	79705.5	24	time	-22.6bp

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=0.8031; (2) sign-flip permutation: each trade's realized move kept, direction re-rolled (variance-matched, stricter for fades), p=0.8001. Verdict uses the stricter p=0.8031 (2000 trials, seed 42, reproducible)
The null must match the live procedure trade-for-trade: every surrogate fills the same count (195 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 [-63bp, -2bp] — 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.