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-MNILUSDT rose 138% on 21 September 2026
Picked after the rise, on one market; all matches came within 30 days.
Next stepWhat happened
Price opened the 18:00 hour at 0.06273 and reached a highest trade of 0.1495 in the 05:00 hour; the tested readings were taken at 17:45.
What stood out at 17:45
- Order book tilt0.8656Tested: 0.86 or higher
- Containment (15m)insideTested: is inside
- How many times the broken descending resistance had been tested4Tested: 3 or higher
17:45 always meets its own rules.
What the record says
More often than any NIL minute, in this sample
Price at least 2% higher after 30 minutes
241 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 · 241 of 43,201 minutes · saved text
- Order book tilt 0.86 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.86 · feature.book_imbalance
- Containment (15m) is inside.Containment · 15m inside · feature.candle_containment_15m
- How many times the broken descending resistance had been tested 3 or higher.how many times the broken descending resistance had been tested ≥ 3 · feature.desc_resistance_broken_touches
Read at 15 minutes before the move.
Read at 17:45 UTC on 21 September, 15 minutes before the selected 18:00 start.
NIL 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 NIL 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 18:00 start was picked automatically after the move.
NILUSDT 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#ffe93e89 @ 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 are common here: 241 of the 43,201 minutes searched (0.6%), about 7.8 a day. What followed was close to a coin flip: 121 rose and 120 fell over the next 30 minutes (241 of the 241 matches have a complete 30 minutes forward).
After 1 hour this setup rose 2% or more in 32 of 241 complete windows (13.3%), against 9.9% with no condition (4,258 of 43,119): 1.34x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 27 of its 241 windows overlap the rise.
Best point inside 1 hour reached +5% or more in 16 of 241 complete windows; worst point fell 5% or more in 9 of 241.
About 7.8 a day, on 30 of 31 days: spread through the record rather than one event.
These 30 days are in a row, so the matches are closer to one episode than a spread. It counts the single minute on 28 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared 62 times in the 43,201 minutes searched (0.1%). What followed was more often lower: 35 of the 62 matches with a complete 30 minutes forward fell (56%).
After 30 minutes this setup fell 2% or more in 7 of 62 complete windows (11.3%), against 5.2% with no condition (2,223 of 43,149): 2.19x.
About 2 a day, on 17 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this are common here: 601 of the 43,201 minutes searched (1.4%), about 19 a day. What followed was close to a coin flip: 291 rose and 309 fell over the next 30 minutes (600 of the 601 matches have a complete 30 minutes forward).
After 30 minutes this setup rose 2% or more in 53 of 600 complete windows (8.8%), against 6.7% with no condition (2,871 of 43,149): 1.33x.
About 19 a day, on 30 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; all 241 matches came from 29 August to 27 September, 27 during the rise.
When the matches happened30 days in a row
- 29 Aug8 matches
- 30 Aug11 matches
- 31 Aug10 matches
- 1 Sep7 matches
- 2 Sep10 matches
- 3 Sep8 matches
- 4 Sep7 matches
- 5 Sep8 matches
- 6 Sep8 matches
- 7 Sep9 matches
- 8 Sep8 matches
- 9 Sep7 matches
- 10 Sep5 matches
- 11 Sep2 matches
- 12 Sep3 matches
- 13 Sep5 matches
- 14 Sep3 matches
- 15 Sep7 matches
- 16 Sep7 matches
- 17 Sep8 matches
- 18 Sep7 matches
- 19 Sep10 matches
- 20 Sep5 matches
- 21 Sep10 matches
- 22 Sep10 matches
- 23 Sep12 matches
- 24 Sep12 matches
- 25 Sep10 matches
- 26 Sep12 matches
- 27 Sep12 matches
Of the 241 matches, 171 came before the rise began, 27 during it and 43 after it.
Neighbouring minutes overlap, so these are not 241 separate trials.
Picked after the rise, on one market; all 241 matches came from 29 August to 27 September, 27 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 NIL minute.
- 30 minutes
15 of 241 (6.2%) were 2% or more lower; any NIL minute 2,223 of 43,149 (5.2%).
Every match has a 30-minute close.
At least 27 of these windows overlap the rise.
- 1 hour
21 of 241 (8.7%) were 2% or more lower; any NIL minute 3,559 of 43,119 (8.3%).
Every match has a 1-hour close.
At least 27 of these windows overlap the rise.
- 4 hours
61 of 239 (25.5%) were 2% or more lower; any NIL minute 8,162 of 42,939 (19.0%).
2 without a 4-hour close yet, left out.
At least 27 of these windows overlap the rise.
- 24 hours
82 of 229 (35.8%) were 2% or more lower; any NIL minute 13,443 of 41,739 (32.2%).
12 without a 24-hour close yet, left out.
At least 27 of these windows overlap the rise.
- 72 hours
90 of 207 (43.5%) were 2% or more lower; any NIL minute 17,058 of 38,859 (43.9%).
34 without a 72-hour close yet, left out.
At least 42 of these windows overlap the rise.
- 7 days
72 of 163 (44.2%) were 2% or more lower; any NIL minute 13,170 of 33,099 (39.8%).
78 without a 7-day close yet, left out.
At least 44 of these windows overlap the rise.
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 1 hour.
After 1 hour this setup rose 2% or more in 32 of 241 complete windows (13.3%), against 9.9% with no condition (4,258 of 43,119): 1.34x.
At least 27 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 1 hour, not the close):
Best point inside 1 hour reached +5% or more in 16 of 241 complete windows; worst point fell 5% or more in 9 of 241.
Picked after the rise, on one market; all 241 matches came from 29 August to 27 September, 27 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 18:00 UTC · 11 of 88 stood out
Order book tilt 0.99 or higher15-minute range against usual 3.3 or higher1-hour range against usual 6.1 or higherLiquidation bunching 0.54 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreVolatility rank 0.99 or higher15-minute price change 0.033 or higher1-hour price change 0.1 or higherDistance from the day's average price 0.097 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.998 ≥ 0.99 Compression · 15m feature.candle_compression_15m 3.335 ≥ 3.3 Compression · 1h feature.candle_compression_1h 6.115 ≥ 6.1 Cascade clustering feature.cascade_clustering_index 0.5438 ≥ 0.54 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 312 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 5 ≥ 3 Realized vol percentile feature.realized_vol_pctrank 1 ≥ 0.99 Return · 15m feature.ret_15m 0.03344 ≥ 0.033 Return · 1h feature.ret_1h 0.1082 ≥ 0.1 VWAP distance · day feature.vwap_dist 0.09719 ≥ 0.097 4 hours before · 21 Sep 14:00 UTC · 7 of 88 stood out
Order book lopsidedness 0.059 or lowerHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change -0.031 or lowerDistance from the day's average price -0.039 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.05868 ≤ 0.059 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 332 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 5 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 20 12 to 720 Return · 1h feature.ret_1h -0.03148 ≤ -0.031 VWAP distance · day feature.vwap_dist -0.03957 ≤ -0.039 1 hour before · 21 Sep 17:00 UTC · 6 of 88 stood out
Order book tilt -0.77 or lowerHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursDistance from the day's average price -0.022 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.7714 ≤ -0.77 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 335 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 5 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 23 12 to 720 VWAP distance · day feature.vwap_dist -0.02254 ≤ -0.022 15 minutes before · 21 Sep 17:45 UTC · 8 of 88 stood out
Order book tilt 0.86 or higherContainment (15m) is insideHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change -0.021 or lowerDistance from the day's average price -0.05 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8656 ≥ 0.86 Containment · 15m feature.candle_containment_15m inside inside 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 335.8 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 5 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 23.75 12 to 720 Return · 1h feature.ret_1h -0.02157 ≤ -0.021 VWAP distance · day feature.vwap_dist -0.0502 ≤ -0.05 1 minute before · 21 Sep 17:59 UTC · 8 of 88 stood out
Order book lopsidedness 0.043 or lowerContainment (15m) is insideHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change -0.032 or lowerDistance from the day's average price -0.052 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.04243 ≤ 0.043 Containment · 15m feature.candle_containment_15m inside inside 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 336 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 5 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 23.98 12 to 720 Return · 1h feature.ret_1h -0.03203 ≤ -0.032 VWAP distance · day feature.vwap_dist -0.05288 ≤ -0.052
Two other reading times we tried 62 and 601 matches
1 minute before (17:59): order book lopsidedness 0.043 or lower, containment (15m) is inside, how many times the broken descending resistance had been tested 3 or higher.
Book imbalance percentile ≤ 0.043 and Containment · 15m inside and how many times the broken descending resistance had been tested ≥ 3
62 matches: price was 2% or more higher after 30 minutes in 7 of 62 (11.3%), and 2% or more lower in 7 of 62 (11.3%).
Of the 62 matches, 28 came before the rise began, 9 during it and 25 after it.
1 hour before (17:00): order book tilt -0.77 or lower, how many times the broken descending resistance had been tested 3 or higher, how long ago the descending resistance broke between 12 and 720.
Book imbalance · top levels ≤ -0.77 and how many times the broken descending resistance had been tested ≥ 3 and how long ago the descending resistance broke 12 to 720
601 matches: price was 2% or more higher after 30 minutes in 53 of 600 (8.8%), and 2% or more lower in 29 of 600 (4.8%).
Of the first 400 of 601 matches checked, 264 came before the rise began, 53 during it and 83 after it.
The saved study leads with 17:45: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market; all 241 matches came from 29 August to 27 September, 27 during the rise.
Hourly candles around the risefull context, lead-up, move
The 18:00 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
- This market only
- The 608 eligible crypto markets · No result for these markets has been measured.
- Every recorded market
- 57 AI sector markets
- 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.