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-MBTWUSDT rose 42% on 21 September 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 20:00 hour at 0.9678 and reached a highest trade of 1.378 in the 01:00 hour; the tested readings were taken at 19:59.
What stood out at 19:59
- Order book tilt0.9618Tested: 0.96 or higher
- Containment (15m)insideTested: is inside
- Liquidation bunching0.597Tested: 0.59 or higher
19:59 always meets its own rules.
What the record says
About as often as any BTW minute
Price at least 2% higher after 30 minutes
70 matches in 43,201 minutes checked.
Picked after the rise, on one market.
Evidence
Does it hold on other markets?
No result for these markets has been measured; nothing runs until you press Run.
Exactly what was counted3 conditions · 70 of 43,201 minutes · saved text
- Order book tilt 0.96 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.96 · feature.book_imbalance
- Containment (15m) is inside.Containment · 15m inside · feature.candle_containment_15m
- Liquidation bunching 0.59 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.59 · feature.cascade_clustering_index
Read at 1 minute before the move.
Read at 19:59 UTC on 21 September, one minute before the selected 20:00 start.
BTW only, 29 August to 27 September 2026 (UTC, ending 28 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every BTW 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 20:00 start was picked automatically after the move.
BTWUSDT stored readings end 2026-09-28 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#06ba9919 @ dataset 1ae64ce7, counted 28 Sep 2026 08:22 UTC.
Saved summary text, as written 28 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 70 times in the 43,201 minutes searched (0.2%). What followed was close to a coin flip: 38 rose and 32 fell over the next 30 minutes (70 of the 70 matches have a complete 30 minutes forward).
After 7 days this setup fell 2% or more in 4 of 45 complete windows (8.9%), against 3.5% with no condition (1,170 of 33,121): 2.52x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 16 of its 45 windows overlap the rise.
Best point inside 7 days reached +5% or more in 44 of 45 complete windows; worst point fell 5% or more in 40 of 45.
At least 39 windows did both.
About 2.3 a day, on 23 of 31 days: spread through the record rather than one event.
It counts the single minute on 28 September as a day.
The other reading times, as written
From 15 minutes before
Minutes like this are common here: 250 of the 36,421 minutes searched (0.7%), about 8.1 a day. What followed was close to a coin flip: 137 rose and 113 fell over the next 30 minutes (250 of the 250 matches have a complete 30 minutes forward).
After 72 hours this setup fell 2% or more in 71 of 213 complete windows (33.3%), against 19.9% with no condition (7,742 of 38,881): 1.67x.
About 8.1 a day, on 22 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 27 times in the 43,201 minutes searched. What followed was more often lower: 15 of the 27 matches with a complete 30 minutes forward fell (56%).
12 rose and 15 fell over 27 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 14 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 70 matches came on 23 of 30 days, 11 during the rise.
When the matches happened23 of 30 days
- 29 Aug3 matches
- 2 Sep3 matches
- 3 Sep3 matches
- 4 Sep3 matches
- 5 Sep1 match
- 6 Sep1 match
- 7 Sep4 matches
- 8 Sep2 matches
- 9 Sep3 matches
- 10 Sep4 matches
- 13 Sep1 match
- 14 Sep1 match
- 15 Sep5 matches
- 16 Sep5 matches
- 17 Sep2 matches
- 20 Sep4 matches
- 21 Sep6 matches
- 22 Sep2 matches
- 23 Sep2 matches
- 24 Sep6 matches
- 25 Sep1 match
- 26 Sep3 matches
- 27 Sep5 matches
No matches on the other 7 days.
Of the 70 matches, 51 came before the rise began, 11 during it and 8 after it.
Neighbouring minutes overlap, so these are not 70 separate trials.
Picked after the rise, on one market; the 70 matches came on 23 of 30 days, 11 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 BTW minute.
- 30 minutes
4 of 70 (5.7%) were 2% or more lower; any BTW minute 2,707 of 43,171 (6.3%).
Every match has a 30-minute close.
At least 11 of these windows overlap the rise.
- 1 hour
7 of 70 (10.0%) were 2% or more lower; any BTW minute 4,348 of 43,141 (10.1%).
Every match has a 1-hour close.
At least 11 of these windows overlap the rise.
- 4 hours
18 of 70 (25.7%) were 2% or more lower; any BTW minute 8,211 of 42,961 (19.1%).
Every match has a 4-hour close.
At least 11 of these windows overlap the rise.
- 24 hours
19 of 65 (29.2%) were 2% or more lower; any BTW minute 11,717 of 41,761 (28.1%).
5 without a 24-hour close yet, left out.
At least 11 of these windows overlap the rise.
- 72 hours
22 of 61 (36.1%) were 2% or more lower; any BTW minute 7,742 of 38,881 (19.9%).
9 without a 72-hour close yet, left out.
At least 4 of these windows overlap the rise.
- 7 days
4 of 45 (8.9%) were 2% or more lower; any BTW minute 1,170 of 33,121 (3.5%).
25 without a 7-day close yet, left out.
At least 16 of these windows overlap the rise.
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 7 days.
After 7 days this setup fell 2% or more in 4 of 45 complete windows (8.9%), against 3.5% with no condition (1,170 of 33,121): 2.52x.
Only 45 of the 70 matches have a 7-day close, all from 29 August to 20 September, and at least 16 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 7 days, not the close):
Best point inside 7 days reached +5% or more in 44 of 45 complete windows; worst point fell 5% or more in 40 of 45.
At least 39 windows did both, so this describes a very jumpy stretch, not a direction.
Picked after the rise, on one market; the 70 matches came on 23 of 30 days, 11 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 · 20 Sep 20:00 UTC · 7 of 88 stood out
Order book tilt 0.77 or higher1-hour range against usual 0.25 or lowerContainment (15m) is insideLiquidation bunching 0.69 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursDistance from the day's average price 0.037 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.7748 ≥ 0.77 Compression · 1h feature.candle_compression_1h 0.2412 ≤ 0.25 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.6939 ≥ 0.69 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 254 12 to 720 VWAP distance · day feature.vwap_dist 0.03718 ≥ 0.037 4 hours before · 21 Sep 16:00 UTC · 7 of 88 stood out
Order book tilt 0.66 or higher15-minute range against usual 0.22 or lowerLiquidation bunching 0.64 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 1 or lowerDistance from the day's average price 0.1 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.6696 ≥ 0.66 Compression · 15m feature.candle_compression_15m 0.2194 ≤ 0.22 Cascade clustering feature.cascade_clustering_index 0.6404 ≥ 0.64 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 274 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 VWAP distance · day feature.vwap_dist 0.108 ≥ 0.1 1 hour before · 21 Sep 19:00 UTC · 7 of 88 stood out
Order book lopsidedness 0.038 or lowerEngulfing (15m) is bullishLiquidation bunching 0.6 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change 0.032 or higherDistance from the day's average price 0.14 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.03739 ≤ 0.038 Engulfing · 15m feature.candle_engulfing_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.6022 ≥ 0.6 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 277 12 to 720 Return · 1h feature.ret_1h 0.03261 ≥ 0.032 VWAP distance · day feature.vwap_dist 0.1473 ≥ 0.14 15 minutes before · 21 Sep 19:45 UTC · 5 of 88 stood out
Containment (15m) is insideLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursDistance from the day's average price 0.13 or higherShow the full readings
Reading Value at that minute Stored rule Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.597 ≥ 0.59 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 277.8 12 to 720 VWAP distance · day feature.vwap_dist 0.1399 ≥ 0.13 1 minute before · 21 Sep 19:59 UTC · 6 of 88 stood out
Order book tilt 0.96 or higherContainment (15m) is insideLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursDistance from the day's average price 0.13 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9618 ≥ 0.96 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.597 ≥ 0.59 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 278 12 to 720 VWAP distance · day feature.vwap_dist 0.1394 ≥ 0.13
Two other reading times we tried 250 and 27 matches
15 minutes before (19:45): containment (15m) is inside, liquidation bunching 0.59 or higher, touches on the broken resistance 3 or more.
Containment · 15m inside and Cascade clustering ≥ 0.59 and how many times the broken short descending resistance had been tested ≥ 3
250 matches: price was 2% or more higher after 30 minutes in 21 of 250 (8.4%), and 2% or more lower in 19 of 250 (7.6%).
Of the 250 matches, 175 came before the rise began, 47 during it and 28 after it.
1 hour before (19:00): order book lopsidedness 0.038 or lower, engulfing (15m) is bullish, liquidation bunching 0.6 or higher.
Book imbalance percentile ≤ 0.038 and Engulfing · 15m bullish and Cascade clustering ≥ 0.6
27 matches: price was 2% or more higher after 30 minutes in 2 of 27, and 2% or more lower in 3 of 27.
Of the 27 matches, 23 came before the rise began, 2 during it and 2 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 19:59: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market; the 70 matches came on 23 of 30 days, 11 during the rise.
Hourly candles around the risefull context, lead-up, move
The 20:00 start was picked after the move, and the hour before was already rising.
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
- This market only
- The 608 eligible crypto markets · No result for these markets has been measured.
- Every recorded market
- 518 sector crypto markets
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.
Starting defaults and coverage
Starting defaults: 2026-08-29 to 2026-09-28 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.