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-MCOLLECTUSDT fell 81% on 5 September 2026
Picked after the fall, on one market.
What happened
Price opened the 10:00 hour at 0.09222 and reached a lowest trade of 0.01732 in the 22:00 hour; the tested readings were taken at 09:00.
What stood out at 09:00
- Order book tilt0.814Tested: 0.81 or higher
- 4-hour range against usual0.3529Tested: 0.36 or lower
- Containment (15m)insideTested: is inside
09:00 always meets its own rules.
What the record says
Too few results to compare
Price at least 2% lower after 30 minutes
29 matches in 43,201 minutes checked.
Picked after the fall, on one market.
Evidence
No test to open
Multiple recorded sectors: sector_alpha, sector_crypto. Choose one explicitly.
Exactly what was counted3 conditions · 29 of 43,201 minutes · saved text
- Order book tilt 0.81 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.81 · feature.book_imbalance
- 4-hour range against usual 0.36 or lower. The last finished 4-hour candle's high to low range, as a multiple of its usual range.the last four-hour candle range versus its baseline ≤ 0.36 · feature.candle_compression_4h
- Containment (15m) is inside.Containment · 15m inside · feature.candle_containment_15m
Read at 1 hour before the move.
Read at 09:00 UTC on 5 September, one hour before the selected 10:00 start.
COLLECT only, 12 August to 10 September 2026 (UTC, ending 11 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every COLLECT 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 10:00 start was picked automatically after the move.
COLLECTUSDT stored readings end 2026-09-11 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#936083a0 @ dataset d31fb5af, counted 12 Sep 2026 08:01 UTC.
Saved summary text, as written 12 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 only 29 times in the 43,201 minutes searched. What followed was close to a coin flip: 15 rose and 14 fell over the next 30 minutes (29 of the 29 matches have a complete 30 minutes forward).
15 rose and 14 fell over 29 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 0.9 a day, on 11 of 31 days: spread through the record rather than one event.
It counts the single minute on 11 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 9 times in the 43,168 minutes searched. What followed was more often higher: 6 of the 9 matches with a complete 30 minutes forward rose (67%).
6 rose and 3 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 9 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 7 times in the 43,168 minutes searched. What followed was more often higher: 4 of the 7 matches with a complete 30 minutes forward rose (57%).
4 rose and 3 fell over 7 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 0.2 a day, on 7 of 31 days: spread through the record rather than one event.
Picked after the fall, on one market; the 29 matches came on 11 of 30 days, 5 during the fall.
When the matches happened11 of 30 days
- 16 Aug2 matches
- 23 Aug1 match
- 28 Aug2 matches
- 29 Aug3 matches
- 31 Aug3 matches
- 1 Sep3 matches
- 3 Sep3 matches
- 5 Sep1 match
- 6 Sep2 matches
- 8 Sep3 matches
- 10 Sep6 matches
No matches on the other 19 days.
Of the 29 matches, 18 came before the fall began, 5 during it and 6 after it.
Neighbouring minutes overlap, so these are not 29 separate trials.
Picked after the fall, on one market; the 29 matches came on 11 of 30 days, 5 during the fall.
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 lower at each time frame: first the matches, then any COLLECT minute.
- 30 minutes
3 of 29 were 2% or more higher; any COLLECT minute 2,896 of 42,990 (6.7%).
Every match has a 30-minute close.
At least 5 of these windows overlap the fall.
- 1 hour
2 of 29 were 2% or more higher; any COLLECT minute 4,563 of 42,961 (10.6%).
Every match has a 1-hour close.
At least 5 of these windows overlap the fall.
- 4 hours
7 of 27 were 2% or more higher; any COLLECT minute 10,005 of 42,781 (23.4%).
2 without a 4-hour close yet, left out.
At least 5 of these windows overlap the fall.
- 24 hours
7 of 23 were 2% or more higher; any COLLECT minute 17,229 of 41,616 (41.4%).
6 without a 24-hour close yet, left out.
At least 5 of these windows overlap the fall.
- 72 hours
8 of 20 were 2% or more higher; any COLLECT minute 18,438 of 38,743 (47.6%).
9 without a 72-hour close yet, left out.
At least 3 of these windows overlap the fall.
- 7 days
6 of 17 were 2% or more higher; any COLLECT minute 18,558 of 33,014 (56.2%).
12 without a 7-day close yet, left out.
At least 9 of these windows overlap the fall.
Picked after the fall, on one market; the 29 matches came on 11 of 30 days, 5 during the fall.
Readings at five times before the fall24 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 · 4 Sep 10:00 UTC · 13 of 63 stood out
Containment (15m) is insideLiquidation bunching 0.57 or higherThe descending resistance line is active 4hHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720The short descending resistance line is active 4hTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursThe support under the short descending resistance is risingTouches on the resistance 3 or moreThe support under the descending resistance is risingHow many times price has touched the descending resistance 3 or higher15-minute price change -0.013 or lowerShow the full readings
Reading Value at that minute Stored rule Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5727 ≥ 0.57 the descending resistance line feature.desc_resistance_active active_4h active_4h how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 5 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 498 12 to 720 the short descending resistance line feature.desc_resistance_short_active active_4h active_4h 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 220 12 to 720 the support under the short descending resistance feature.desc_resistance_short_support rising rising how many times price has touched the short descending resistance feature.desc_resistance_short_touches 4 ≥ 3 the support under the descending resistance feature.desc_resistance_support rising rising how many times price has touched the descending resistance feature.desc_resistance_touches 4 ≥ 3 Return · 15m feature.ret_15m -0.01375 ≤ -0.013 4 hours before · 5 Sep 06:00 UTC · 10 of 63 stood out
Order book tilt 0.51 or higherContainment (15m) is outsideEngulfing (15m) is bearishLiquidation bunching 0.57 or higherHow many times the broken descending resistance had been tested 3 or higherThe short descending resistance line is active 4hTouches on the broken resistance 3 or moreThe distance from price to the short descending resistance between 0 and 1The support under the short descending resistance is risingTouches on the resistance 3 or moreShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5189 ≥ 0.51 Containment · 15m feature.candle_containment_15m outside outside Engulfing · 15m feature.candle_engulfing_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5795 ≥ 0.57 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 the short descending resistance line feature.desc_resistance_short_active active_4h active_4h how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 4 ≥ 3 the distance from price to the short descending resistance feature.desc_resistance_short_dist_atr 0.2658 0 to 1 the support under the short descending resistance feature.desc_resistance_short_support rising rising how many times price has touched the short descending resistance feature.desc_resistance_short_touches 3 ≥ 3 1 hour before · 5 Sep 09:00 UTC · 13 of 63 stood out
Order book tilt 0.81 or higher4-hour range against usual 0.36 or lowerContainment (15m) is insideSweep + reclaim (1h) is bearishLiquidation bunching 0.58 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720The short descending resistance line is active 4hTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursThe support under the short descending resistance is risingTouches on the resistance 3 or moreDistance from the day's average price 0.02 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.814 ≥ 0.81 the last four-hour candle range versus its baseline feature.candle_compression_4h 0.3529 ≤ 0.36 Containment · 15m feature.candle_containment_15m inside inside Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.5803 ≥ 0.58 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 14 12 to 720 the short descending resistance line feature.desc_resistance_short_active active_4h active_4h how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 4 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 14 12 to 720 the support under the short descending resistance feature.desc_resistance_short_support rising rising how many times price has touched the short descending resistance feature.desc_resistance_short_touches 3 ≥ 3 VWAP distance · day feature.vwap_dist 0.02076 ≥ 0.02 15 minutes before · 5 Sep 09:45 UTC · 17 of 63 stood out
Order book lopsidedness 0.059 or lower15-minute range against usual 3.5 or higher4-hour range against usual 0.36 or lowerSweep + reclaim (1h) is bearishLiquidation bunching 0.58 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720The short descending resistance line is active 4hTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursThe support under the short descending resistance is risingTouches on the resistance 3 or moreOpen interest change rank 0.97 or higherVolatility rank 0.99 or higher15-minute price change 0.044 or higher1-hour price change 0.12 or higherDistance from the day's average price 0.089 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.05815 ≤ 0.059 Compression · 15m feature.candle_compression_15m 3.533 ≥ 3.5 the last four-hour candle range versus its baseline feature.candle_compression_4h 0.3529 ≤ 0.36 Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.5873 ≥ 0.58 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 14.75 12 to 720 the short descending resistance line feature.desc_resistance_short_active active_4h active_4h how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 4 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 14.75 12 to 720 the support under the short descending resistance feature.desc_resistance_short_support rising rising how many times price has touched the short descending resistance feature.desc_resistance_short_touches 3 ≥ 3 OI velocity percentile feature.oi_velocity_pctrank 0.9796 ≥ 0.97 Realized vol percentile feature.realized_vol_pctrank 1 ≥ 0.99 Return · 15m feature.ret_15m 0.04464 ≥ 0.044 Return · 1h feature.ret_1h 0.1262 ≥ 0.12 VWAP distance · day feature.vwap_dist 0.08902 ≥ 0.089 1 minute before · 5 Sep 09:59 UTC · 16 of 63 stood out
Order book lopsidedness 0.067 or lower15-minute range against usual 3.5 or higher4-hour range against usual 0.36 or lowerSweep + reclaim (1h) is bearishLiquidation bunching 0.59 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720The short descending resistance line is active 4hTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursThe support under the short descending resistance is risingTouches on the resistance 3 or moreOpen interest change rank 0.93 or higherVolatility rank 0.99 or higher1-hour price change 0.11 or higherDistance from the day's average price 0.069 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.06626 ≤ 0.067 Compression · 15m feature.candle_compression_15m 3.533 ≥ 3.5 the last four-hour candle range versus its baseline feature.candle_compression_4h 0.3529 ≤ 0.36 Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.5905 ≥ 0.59 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 14.98 12 to 720 the short descending resistance line feature.desc_resistance_short_active active_4h active_4h how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 4 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 14.98 12 to 720 the support under the short descending resistance feature.desc_resistance_short_support rising rising how many times price has touched the short descending resistance feature.desc_resistance_short_touches 3 ≥ 3 OI velocity percentile feature.oi_velocity_pctrank 0.9318 ≥ 0.93 Realized vol percentile feature.realized_vol_pctrank 1 ≥ 0.99 Return · 1h feature.ret_1h 0.1171 ≥ 0.11 VWAP distance · day feature.vwap_dist 0.06933 ≥ 0.069
Two other reading times we tried 9 and 7 matches
1 minute before (09:59): order book lopsidedness 0.067 or lower, open interest change rank 0.93 or higher, volatility rank 0.99 or higher.
Book imbalance percentile ≤ 0.067 and OI velocity percentile ≥ 0.93 and Realized vol percentile ≥ 0.99
9 matches: price was 2% or more lower after 30 minutes in 2 of 9, and 2% or more higher in 4 of 9.
Of the 9 matches, 7 came before the fall began, 1 during it and 1 after it.
15 minutes before (09:45): order book lopsidedness 0.059 or lower, open interest change rank 0.97 or higher, volatility rank 0.99 or higher.
Book imbalance percentile ≤ 0.059 and OI velocity percentile ≥ 0.97 and Realized vol percentile ≥ 0.99
7 matches: price was 2% or more lower after 30 minutes in 2 of 7, and 2% or more higher in 2 of 7.
Of the 7 matches, 6 came before the fall began, 1 during it and 0 after it.
Fewer than 30 results, so no rate is printed.
No set had 30 matches before the fall; the saved study leads with the one that had the most.
Picked after the fall, on one market; the 29 matches came on 11 of 30 days, 5 during the fall.
Hourly candles around the fallfull context, lead-up, move
The 10:00 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: 2026-08-12 to 2026-09-11 UTC; finishes down 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.