Study · re-run every night · updated
What the strategy search keeps, and what it threw away
On the night of Nov 21, 2026, the search tested 3,680 versions of 2,088 trading rules, each buying the coins at one end of a measure and shorting the other end. 85 passed the first cut on the older 60% of their history (with this many tests at once, a luck test of about 3.2 was needed); 16 also earned on the newer 40% they never saw. The book keeps every rule that ever passed: 16 still passing, 14 faded, each paper-traded from the night it was found (the first on Oct 6, 2026). Past patterns, not financial advice.
Tests
3,680
2,088 rules
First cut
85
older 60%
Held
16
newer 40% too
In the book
16
still passing
§ 01 · The night's search
The night's search
as of · the strategy search, Nov 21, 2026
Each rule ranks the coins by one measure (a move, a volatility, a volume, a positioning reading), buys one end and shorts the other, and holds for a set number of days, in every market or only while Bitcoin is above or below its 200-day average. Its oldest periods start Mar 31, 2019; the newer part starts between Aug 28, 2023 and Oct 24, 2026, depending on how long each measure's history is.
§ 02 · What it keeps16 kept
What it keeps
as of · the survivors, counted
16 rules passed both cuts. Across them, the typical rule made +0.90% a period from the coins it bought over the ones it shorted (+0.43% from the bought side alone), with a luck test of 3.2 on the newer part.
- 9 held 1 day
- 5 held 3 days
- 2 held 7 days
- 10 in every market
- 1 only in bull markets
- 5 only in bear markets
- 9 among all the coins
- 7 with the majors, the thinnest, the newest and the wildest left out
The book keeps every rule that ever passed, paper-traded from the night it was found: 16 still passing, 14 faded.
§ 03 · What it threw away
What it threw away: the closest misses
as of · neither proven nor kept
The rules that came closest, in full. Each missed a cut: the dot is its luck test on the older part (against the first cut's bar), the diamond on the newer part (against its own bar).
older partnewer partthe bar each must pass
Rank the coins by their Binance funding over the last week: buy the top 10% and short the bottom 10%, for 1 day, only while Bitcoin is below its 200-day average, leaving out the majors, the thinnest, the newest and the wildest coins.
luck test 2.7 on the older part (trimmed 2.9), 4.6 on the newer · 301 periods · +0.64% a period (trimmed +0.59%, middle +0.51%) · 60% won
Rank the coins by their Binance funding over the last week: buy the top 20% and short the bottom 20%, for 1 day, only while Bitcoin is below its 200-day average, leaving out the majors, the thinnest, the newest and the wildest coins.
luck test 2.4 on the older part (trimmed 2.1), 4.4 on the newer · 301 periods · +0.39% a period (trimmed +0.36%, middle +0.25%) · 60% won
Rank the coins by their Binance funding over the last week: buy the top 10% and short the bottom 10%, for 3 days, only while Bitcoin is below its 200-day average.
luck test 2.6 on the older part (trimmed 2.5), 3.9 on the newer · 100 periods · +2.46% a period (trimmed +2.05%, middle +1.56%) · 67% won
Rank the coins by their Binance funding over the last week: buy the top 20% and short the bottom 20%, for 3 days, only while Bitcoin is below its 200-day average.
luck test 3.0 on the older part (trimmed 2.9), 3.5 on the newer · 100 periods · +1.49% a period (trimmed +1.30%, middle +1.04%) · 67% won
Rank the coins by the last 3 days' move: buy the bottom 20% and short the top 20%, for 1 day, only while Bitcoin is below its 200-day average.
luck test 5.1 on the older part (trimmed 5.5), 1.1 on the newer · 1,120 periods · +0.33% a period (trimmed +0.29%, middle +0.31%) · 58% won · passed the first cut, failed the newer part
Rank the coins by their Binance funding over the last week: buy the top 20% and short the bottom 20%, for 3 days, only while Bitcoin is below its 200-day average, leaving out the majors, the thinnest, the newest and the wildest coins.
luck test 3.0 on the older part (trimmed 2.8), 2.8 on the newer · 100 periods · +1.15% a period (trimmed +1.06%, middle +0.90%) · 66% won
Rank the coins by the last 3 days' move: buy the bottom 10% and short the top 10%, for 1 day, only while Bitcoin is below its 200-day average.
luck test 4.9 on the older part (trimmed 5.5), 0.4 on the newer · 1,120 periods · +0.45% a period (trimmed +0.41%, middle +0.37%) · 56% won · passed the first cut, failed the newer part
Rank the coins by their own volatility over 60 days, Bitcoin's part taken out: buy the bottom 10% and short the top 10%, for 14 days, only while Bitcoin is above its 200-day average.
luck test −0.2 on the older part (trimmed 0.7), 5.0 on the newer · 114 periods · +1.61% a period (trimmed +3.16%, middle +3.83%) · 66% won
§ 04 · How it is tested
How it is tested
as of · methodology
A luck test (t) says how far a result sits from zero, in units of its own noise: about 2 is luck 1 time in 20 or less for one test, but the best of 100 tests clears 2 by luck 9 times in 10, which is what the first cut is for.
Every rule, in every pool and by two detectors (the plain average and an average with the best and worst tenth of periods left out), goes through one 5% false-discovery cut on the older 60% of its own periods. Then, on the newer 40% it was never chosen on, it must earn on the same side with a luck test of 1.645 or more, every period counted: a trader cannot skip the worst ones after the fact.
Our price history holds today's coins: coins that died before we began collecting are missing, which flatters a long side and hurts a short side the further back it goes.
§ 05 · Revisions30 dated
Revisions
as of · every change to its headline numbers, dated
This study is re-run every night on the whole history. It was first written on Oct 6, 2026; its numbers last moved on Nov 21, 2026. Each night its headline numbers moved is listed here, newest first.
- 3,680 tests · 85 past the first cut · 16 held · 16 in the book
- 3,680 tests · 84 past the first cut · 16 held · 16 in the book
- 3,680 tests · 83 past the first cut · 14 held · 14 in the book
- 3,680 tests · 81 past the first cut · 13 held · 13 in the book
- 3,680 tests · 82 past the first cut · 13 held · 13 in the book
- 3,680 tests · 81 past the first cut · 11 held · 11 in the book
- 3,680 tests · 80 past the first cut · 15 held · 15 in the book
- 3,680 tests · 75 past the first cut · 15 held · 15 in the book
- 3,680 tests · 76 past the first cut · 15 held · 15 in the book
- 3,680 tests · 77 past the first cut · 18 held · 18 in the book
- 3,680 tests · 78 past the first cut · 17 held · 17 in the book
- 3,680 tests · 82 past the first cut · 18 held · 18 in the book
- 3,680 tests · 78 past the first cut · 17 held · 17 in the book
- 3,664 tests · 72 past the first cut · 13 held · 13 in the book
- 3,662 tests · 74 past the first cut · 13 held · 13 in the book
- 3,646 tests · 73 past the first cut · 12 held · 12 in the book
- 3,630 tests · 73 past the first cut · 12 held · 12 in the book
- 3,628 tests · 72 past the first cut · 13 held · 13 in the book
- 3,628 tests · 70 past the first cut · 11 held · 11 in the book
- 3,628 tests · 69 past the first cut · 11 held · 11 in the book
- 3,628 tests · 70 past the first cut · 12 held · 12 in the book
- 3,628 tests · 67 past the first cut · 9 held · 9 in the book
- 3,628 tests · 69 past the first cut · 10 held · 10 in the book
- 3,628 tests · 70 past the first cut · 11 held · 11 in the book
- 3,628 tests · 68 past the first cut · 10 held · 10 in the book
- 3,628 tests · 70 past the first cut · 10 held · 10 in the book
- 3,628 tests · 70 past the first cut · 11 held · 11 in the book
- 3,626 tests · 65 past the first cut · 11 held · 11 in the book
- 3,338 tests · 60 past the first cut · 10 held · 10 in the book
- 3,144 tests · 55 past the first cut · 8 held · 8 in the book
§ 06 · More
More research
as of
Get the day's plays in your Telegram before they go out on X, tested like this one → 7 days of Pro free · no payment