Research is a work in progress. Estimated release: 1 December 2026. Our goal is to make it a search engine for trading setups in recorded crypto markets.
Binance USDT-MBULLAUSDT rose 82% on 6 September 2026
Picked after the rise, on one market.
What happened
Price opened the 08:00 hour at 0.07016 and reached a highest trade of 0.1276 in the 12:00 hour; the tested readings were taken at 07:45.
What stood out at 07:45
- Order book tilt0.9453Tested: 0.94 or higher
- Sweep + reclaim (15m)bullishTested: is bullish
- Liquidation bunching0.5412Tested: 0.54 or higher
07:45 always meets its own rules.
What the record says
More often than any BULLA minute, in this sample
Price at least 2% higher after 30 minutes
32 matches in 43,201 minutes checked.
Picked after the rise, on one market.
Evidence
No test to open
Multiple recorded sectors: sector_alpha, sector_crypto. Choose one explicitly.
Exactly what was counted3 conditions · 32 of 43,201 minutes · saved text
- Order book tilt 0.94 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.94 · feature.book_imbalance
- Sweep + reclaim (15m) is bullish.Sweep + reclaim · 15m bullish · feature.candle_sweep_reclaim_15m
- Liquidation bunching 0.54 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.54 · feature.cascade_clustering_index
Read at 15 minutes before the move.
Read at 07:45 UTC on 6 September, 15 minutes before the selected 08:00 start.
BULLA only, 14 August to 12 September 2026 (UTC, ending 13 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every BULLA minute over the same dates, matches included; it is not a matched control group.
Outcome: the close exactly 30 minutes later, not the highest or lowest price along the way.
The 08:00 start was picked automatically after the move.
BULLAUSDT stored readings end 2026-09-13 00:00 UTC (exclusive). Prices and tick replay have separate coverage.
The feature manifest spans the lead-up. Individual minutes or inputs can still be unavailable.
This is not a similarity search. Each count matches the exact readings above and nothing else.
Picked in hindsight: the counts include every other time these readings appeared, not just this move.
Fires often arrive as clusters of consecutive minutes, and forward windows overlap. A cluster is one episode, not many independent trials.
If these counts read weaker than the move suggested, that is the tool working: the lead-up of a picked move always looks special until it is counted everywhere else.
Saved study q#86a3e71b @ dataset 0848795c, counted 13 Sep 2026 08:14 UTC.
Saved summary text, as written 13 Sep 2026
Written automatically when this study was saved and kept as written; where a line differs from the counts above, the counts govern.
Minutes like this appeared 32 times in the 43,201 minutes searched (<0.1%). What followed was more often higher: 18 of the 32 matches with a complete 30 minutes forward rose (56%).
After 30 minutes this setup fell 2% or more in 5 of 32 complete windows (15.6%), against 6.8% with no condition (2,914 of 43,123): 2.31x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 8 of its 32 windows overlap the rise.
Best point inside 30 minutes reached +5% or more in 4 of 32 complete windows; worst point fell 5% or more in 5 of 32.
About 1 a day, on 13 of 31 days: spread through the record rather than one event.
It counts the single minute on 13 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 15 times in the 43,201 minutes searched. What followed was more often higher: 13 of the 15 matches with a complete 30 minutes forward rose (87%).
13 rose and 2 fell over 15 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
About 0.5 a day, on 12 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 9 times in the 43,201 minutes searched. What followed was more often lower: 6 of the 9 matches with a complete 30 minutes forward fell (67%).
3 rose and 6 fell over 9 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
About 0.3 a day, on 8 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 32 matches came on 13 of 30 days, 8 during the rise.
When the matches happened13 of 30 days
- 14 Aug2 matches
- 16 Aug4 matches
- 30 Aug3 matches
- 1 Sep1 match
- 2 Sep1 match
- 4 Sep2 matches
- 5 Sep2 matches
- 6 Sep2 matches
- 7 Sep5 matches
- 8 Sep3 matches
- 10 Sep1 match
- 11 Sep4 matches
- 12 Sep2 matches
No matches on the other 17 days.
Of the 32 matches, 17 came before the rise began, 8 during it and 7 after it.
Neighbouring minutes overlap, so these are not 32 separate trials.
Picked after the rise, on one market; the 32 matches came on 13 of 30 days, 8 during the rise.
Other time frames30 minutes to 7 days
The answer uses 30 minutes, the time frame this study counted by default. Each row counts the same matches at a later close, in both directions. The bars show how often price was 2% or more higher at each time frame: first the matches, then any BULLA minute.
- 30 minutes
5 of 32 (15.6%) were 2% or more lower; any BULLA minute 2,914 of 43,123 (6.8%).
Every match has a 30-minute close.
At least 8 of these windows overlap the rise.
- 1 hour
6 of 32 (18.8%) were 2% or more lower; any BULLA minute 4,288 of 43,093 (10.0%).
Every match has a 1-hour close.
At least 8 of these windows overlap the rise.
- 4 hours
7 of 32 (21.9%) were 2% or more lower; any BULLA minute 7,195 of 42,913 (16.8%).
Every match has a 4-hour close.
At least 8 of these windows overlap the rise.
- 24 hours
6 of 30 (20.0%) were 2% or more lower; any BULLA minute 10,591 of 41,713 (25.4%).
2 without a 24-hour close yet, left out.
At least 8 of these windows overlap the rise.
- 72 hours
3 of 25 were 2% or more lower; any BULLA minute 13,074 of 38,836 (33.7%).
7 without a 72-hour close yet, left out.
At least 12 of these windows overlap the rise.
- 7 days
4 of 15 were 2% or more lower; any BULLA minute 12,404 of 33,077 (37.5%).
17 without a 7-day close yet, left out.
At least 6 of these windows overlap the rise.
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 30 minutes.
After 30 minutes this setup fell 2% or more in 5 of 32 complete windows (15.6%), against 6.8% with no condition (2,914 of 43,123): 2.31x.
At least 8 of those windows ran through the rise itself, so it partly counts the rise as an outcome.
Along the way (the highest and lowest price inside 30 minutes, not the close):
Best point inside 30 minutes reached +5% or more in 4 of 32 complete windows; worst point fell 5% or more in 5 of 32.
Picked after the rise, on one market; the 32 matches came on 13 of 30 days, 8 during the rise.
Readings at five times before the rise24 hours to 1 minute before · 2 other times tried
Highlights follow fixed rules, not significance tests. Proposed conditions round values or use ranges; inspect them before running.
24 hours before · 5 Sep 08:00 UTC · 13 of 63 stood out
Order book tilt 0.84 or higher4-hour range against usual 2.3 or higherSweep + reclaim (15m) is bearishSweep + reclaim (1h) is bearishUpper wick (15m) 0.68 or higherLiquidation bunching 0.73 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 1 or lowerOpen interest change rank 0.91 or higher15-minute price change 0.028 or higher1-hour price change 0.059 or higherDistance from the day's average price 0.31 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8473 ≥ 0.84 the last four-hour candle range versus its baseline feature.candle_compression_4h 2.321 ≥ 2.3 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Upper wick · 15m feature.candle_upper_wick_15m 0.6888 ≥ 0.68 Cascade clustering feature.cascade_clustering_index 0.7366 ≥ 0.73 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 74 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 OI change magnitude score feature.oi_velocity_pctrank 0.9126 ≥ 0.91 Return · 15m feature.ret_15m 0.02859 ≥ 0.028 Return · 1h feature.ret_1h 0.05999 ≥ 0.059 VWAP distance · day feature.vwap_dist 0.3112 ≥ 0.31 4 hours before · 6 Sep 04:00 UTC · 9 of 63 stood out
Order book tilt 0.92 or higherEngulfing (15m) is bullishLiquidation bunching 0.58 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursOpen interest change rank 0.1 or lower15-minute price change 0.018 or higher1-hour price change 0.036 or higherDistance from the day's average price 0.026 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9267 ≥ 0.92 Engulfing · 15m feature.candle_engulfing_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.5833 ≥ 0.58 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 94 12 to 720 OI change magnitude score feature.oi_velocity_pctrank 0.09948 ≤ 0.1 Return · 15m feature.ret_15m 0.01884 ≥ 0.018 Return · 1h feature.ret_1h 0.03663 ≥ 0.036 VWAP distance · day feature.vwap_dist 0.02685 ≥ 0.026 1 hour before · 6 Sep 07:00 UTC · 8 of 63 stood out
Order book tilt -0.99 or lowerEngulfing (15m) is bearishLiquidation bunching 0.53 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours15-minute price change -0.021 or lower1-hour price change -0.039 or lowerDistance from the day's average price -0.034 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9989 ≤ -0.99 Engulfing · 15m feature.candle_engulfing_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5398 ≥ 0.53 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 97 12 to 720 Return · 15m feature.ret_15m -0.02103 ≤ -0.021 Return · 1h feature.ret_1h -0.03995 ≤ -0.039 VWAP distance · day feature.vwap_dist -0.03452 ≤ -0.034 15 minutes before · 6 Sep 07:45 UTC · 9 of 63 stood out
Order book tilt 0.94 or higherSweep + reclaim (15m) is bullishLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 15 or lower15-minute price change -0.041 or lower1-hour price change -0.17 or lowerDistance from the day's average price -0.15 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9453 ≥ 0.94 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.5412 ≥ 0.54 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 97.75 12 to 720 Minutes to funding feature.mins_to_funding 15 ≤ 15 Return · 15m feature.ret_15m -0.04147 ≤ -0.041 Return · 1h feature.ret_1h -0.1767 ≤ -0.17 VWAP distance · day feature.vwap_dist -0.1598 ≤ -0.15 1 minute before · 6 Sep 07:59 UTC · 10 of 63 stood out
Order book tilt -0.5 or lowerSweep + reclaim (15m) is bullishLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 1 or lowerVolatility rank 0.93 or higher15-minute price change 0.056 or higher1-hour price change -0.1 or lowerDistance from the day's average price -0.1 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5055 ≤ -0.5 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.5428 ≥ 0.54 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 97.98 12 to 720 Minutes to funding feature.mins_to_funding 1 ≤ 1 Realized vol percentile feature.realized_vol_pctrank 0.9345 ≥ 0.93 Return · 15m feature.ret_15m 0.05641 ≥ 0.056 Return · 1h feature.ret_1h -0.1077 ≤ -0.1 VWAP distance · day feature.vwap_dist -0.1029 ≤ -0.1
Two other reading times we tried 15 and 9 matches
1 minute before (07:59): order book tilt -0.5 or lower, sweep + reclaim (15m) is bullish, volatility rank 0.93 or higher.
Book imbalance · top levels ≤ -0.5 and Sweep + reclaim · 15m bullish and Realized vol percentile ≥ 0.93
15 matches: price was 2% or more higher after 30 minutes in 3 of 15, and 2% or more lower in 2 of 15.
Of the 15 matches, 11 came before the rise began, 3 during it and 1 after it.
1 hour before (07:00): order book tilt -0.99 or lower, engulfing (15m) is bearish, liquidation bunching 0.53 or higher.
Book imbalance · top levels ≤ -0.99 and Engulfing · 15m bearish and Cascade clustering ≥ 0.53
9 matches: price was 2% or more higher after 30 minutes in 0 of 9, and 2% or more lower in 2 of 9.
Of the 9 matches, 6 came before the rise began, 2 during it and 1 after it.
Fewer than 30 results, so no rate is printed.
No set had 30 matches before the rise; the saved study leads with the one that had the most.
Picked after the rise, on one market; the 32 matches came on 13 of 30 days, 8 during the rise.
Hourly candles around the risefull context, lead-up, move
The 08:00 start was picked after the move.
Hourly candles, UTC. The marked lines are the minutes the readings came from: 1 minute, 15 minutes, 1 hour, 4 hours and 24 hours before the selected start.
Other ways to test itsame dates
Multiple recorded sectors: sector_alpha, sector_crypto. Choose one explicitly.
Each opens Review the test; nothing runs until you press Run.
Running needs a free account and uses your allowance; you see the cost first.
Starting defaults and coverage
Starting defaults: 2026-08-14 to 2026-09-13 UTC; finishes up 2% or more after 1 hour. Review or change the markets, dates, conditions and outcome before running. Current recorded classification and sector tags, not point-in-time membership. Historical membership may differ. Instrument history does not guarantee every setup input or outcome is present; actual study exclusions remain authoritative.