Pattern miner
What is actually in the history?
Mined from captured snapshots · train and holdout shown side by side
hypotheses only · nothing here is a signal
Snapshots available
18,834 captured
100 needed to mine
These are the live 1-minute capture snapshots, not the
5-year option-chain backfill. They are two different datasets: this one
fills every minute the market is open; the other is what /thesis is
still waiting on.
Patterns
BEARISH
B_7884b5a6
VALIDATED
train67.9%
holdout75.5%
-7.6 pts train → holdout
- expectancy
- 11.2 pts
- average move
- -11.2 pts
- median move
- -9.1 pts
- worst drawdown
- 88.5 pts
- sample · holdout
- 446 · 49
- measured over
- 15 min
global_risk_sentiment Bearishoi_change_call 41.227
BEARISH
B_a0eb2da1
VALIDATED
train62.7%
holdout69.2%
-6.5 pts train → holdout
- expectancy
- 11.5 pts
- average move
- -11.5 pts
- median move
- -11.9 pts
- worst drawdown
- 73.8 pts
- sample · holdout
- 134 · 52
- measured over
- 15 min
liquidity_outcome DOWNGRADEconstituent_agree_count 8.0
BULLISH
B_da05f98e
VALIDATED
train65.6%
holdout65.9%
-0.3 pts train → holdout
- expectancy
- 12.0 pts
- average move
- 12.0 pts
- median move
- 7.9 pts
- worst drawdown
- 29.6 pts
- sample · holdout
- 32 · 41
- measured over
- 15 min
institutional_confirmation_outcome UNCONFIRMEDfutures_volume 1798485.0
BEARISH
B_79ea2c8a
VALIDATED
train64.3%
holdout65.5%
-1.2 pts train → holdout
- expectancy
- 13.5 pts
- average move
- -13.5 pts
- median move
- -12.4 pts
- worst drawdown
- 73.8 pts
- sample · holdout
- 143 · 58
- measured over
- 15 min
liquidity_outcome DOWNGRADEoi_change_put 39.02
BEARISH
B_bea91b7f
VALIDATED
train63.3%
holdout65.5%
-2.2 pts train → holdout
- expectancy
- 12.9 pts
- average move
- -12.9 pts
- median move
- -12.2 pts
- worst drawdown
- 73.8 pts
- sample · holdout
- 139 · 58
- measured over
- 15 min
liquidity_outcome DOWNGRADEfutures_volume 804505.0
BEARISH
B_23240d28
VALIDATED
train63.3%
holdout61.3%
+2.0 pts train → holdout
- expectancy
- 12.9 pts
- average move
- -12.9 pts
- median move
- -12.2 pts
- worst drawdown
- 73.8 pts
- sample · holdout
- 139 · 62
- measured over
- 15 min
liquidity_outcome DOWNGRADEoi_change_call 41.227
BULLISH
B_9643d1f0
VALIDATED
train72.6%
holdout59.8%
+12.8 pts train → holdout
- expectancy
- 11.3 pts
- average move
- 11.3 pts
- median move
- 9.2 pts
- worst drawdown
- 29.6 pts
- sample · holdout
- 62 · 82
- measured over
- 15 min
fii_net 0.0futures_volume 1798485.0
BEARISH
B_5a1edde7
VALIDATED
train73.0%
holdout58.3%
+14.7 pts train → holdout
- expectancy
- 11.7 pts
- average move
- -11.7 pts
- median move
- -8.1 pts
- worst drawdown
- 22.2 pts
- sample · holdout
- 63 · 12
- measured over
- 15 min
dealer_intelligence_readable POSITIVE_GAMMA, close to flip (regime could reverse on a small move), velocity moving toward POSITIVE_GAMMA (dampening).iv_agreement_score 0.8
BULLISH
B_92b73e22
VALIDATED
train57.1%
holdout58.2%
-1.1 pts train → holdout
- expectancy
- 10.1 pts
- average move
- 10.1 pts
- median move
- 8.9 pts
- worst drawdown
- 41.0 pts
- sample · holdout
- 70 · 55
- measured over
- 15 min
institutional_confirmation_outcome UNCONFIRMEDoi_change_put 39.02
BEARISH
B_a7411975
VALIDATED
train55.8%
holdout57.9%
-2.1 pts train → holdout
- expectancy
- 21.1 pts
- average move
- -21.1 pts
- median move
- -11.4 pts
- worst drawdown
- 73.8 pts
- sample · holdout
- 43 · 19
- measured over
- 15 min
liquidity_outcome DOWNGRADEfutures_oi 14098500.0
How to read this
Train is how often the pattern worked on the data it
was found in. Holdout is how often it worked on data it had never
seen. A big drop between them means the pattern was fitted to noise — and
a miner reporting only the training number will find a beautiful pattern
in pure randomness, every time.
The 50% line is drawn on every bar because that is the
coin flip these have to beat. A mined pattern is a hypothesis. None
of them reaches a trade, a score, or a size until it survives a real
forward test.