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-MLSKUSDT rose 945% on 12 September 2026
Picked after the rise, on one market; all matches came within 24 days.
What happened
Price opened the 21:00 hour at 0.2268 and reached a highest trade of 2.37 in the 03:00 hour; the tested readings were taken at 20:00.
What stood out at 20:00
- Order book lopsidedness0.04851Tested: 0.049 or lower
- How many times the broken descending resistance had been tested6Tested: 3 or higher
- How long ago the descending resistance broke84Tested: between 12 and 720
20:00 always meets its own rules.
What the record says
More often than any LSK minute, in this sample
Price at least 2% higher after 30 minutes
375 matches in 35,281 minutes checked; 4 missing a 30-minute close, left out.
Picked after the rise, on one market.
Evidence
No test to open
Multiple recorded sectors: sector_crypto, sector_layer_2. Choose one explicitly.
Exactly what was counted3 conditions · 375 of 35,281 minutes · saved text
- Order book lopsidedness 0.049 or lower. How lopsided the sizes at the best bid and ask were, either way, against recent readings; low means unusually even.Book imbalance percentile ≤ 0.049 · feature.book_imbalance_pctrank
- 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
- How long ago the descending resistance broke between 12 and 720.how long ago the descending resistance broke 12 to 720 · feature.desc_resistance_hours_since_break
Read at 1 hour before the move.
Read at 20:00 UTC on 12 September, one hour before the selected 21:00 start.
LSK only, 19 August to 17 September 2026 (UTC, ending 18 September 00:00); all 3 readings had values on 35,281 of those minutes.
Reference: every LSK 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 21:00 start was picked automatically after the move.
LSKUSDT stored readings end 2026-09-18 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#e69c901d @ dataset 8904ef04, counted 18 Sep 2026 09:26 UTC.
Saved summary text, as written 18 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: 375 of the 35,281 minutes searched (1.1%), about 12 a day. What followed was close to a coin flip: 191 rose and 180 fell over the next 30 minutes (371 of the 375 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 49 of 371 complete windows (13.2%), against 8.0% with no condition (3,453 of 42,900): 1.64x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 5 of its 371 windows overlap the rise.
Best point inside 30 minutes reached +5% or more in 43 of 374 complete windows; worst point fell 5% or more in 43 of 374.
About 12 a day, on 24 of 31 days: spread through the record rather than one event.
These 24 days are in a row, so the matches are closer to one episode than a spread. It counts the single minute on 18 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 3 times in the 35,281 minutes searched. What followed was more often lower: 2 of the 3 matches with a complete 30 minutes forward fell (67%).
1 rose and 2 fell over 3 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 0.1 a day, on 3 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this are common here: 431 of the 35,281 minutes searched (1.2%), about 14 a day. What followed was close to a coin flip: 222 rose and 206 fell over the next 30 minutes (428 of the 431 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 55 of 428 complete windows (12.9%), against 8.0% with no condition (3,453 of 42,900): 1.60x.
About 14 a day, on 24 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; all 375 matches came from 25 August to 17 September, 5 during the rise.
When the matches happened24 days in a row
- 25 Aug15 matches
- 26 Aug19 matches
- 27 Aug13 matches
- 28 Aug19 matches
- 29 Aug7 matches
- 30 Aug11 matches
- 31 Aug17 matches
- 1 Sep14 matches
- 2 Sep11 matches
- 3 Sep14 matches
- 4 Sep9 matches
- 5 Sep15 matches
- 6 Sep14 matches
- 7 Sep16 matches
- 8 Sep17 matches
- 9 Sep9 matches
- 10 Sep18 matches
- 11 Sep18 matches
- 12 Sep18 matches
- 13 Sep19 matches
- 14 Sep20 matches
- 15 Sep21 matches
- 16 Sep21 matches
- 17 Sep20 matches
No matches on the other 6 days.
Of the 375 matches, 272 came before the rise began, 5 during it and 98 after it.
Neighbouring minutes overlap, so these are not 375 separate trials.
Picked after the rise, on one market; all 375 matches came from 25 August to 17 September, 5 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 LSK minute.
- 30 minutes
49 of 371 (13.2%) were 2% or more lower; any LSK minute 3,453 of 42,900 (8.0%).
4 without a 30-minute close yet, left out.
At least 5 of these windows overlap the rise.
- 1 hour
54 of 373 (14.5%) were 2% or more lower; any LSK minute 4,255 of 42,872 (9.9%).
2 without a 1-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 4 hours
72 of 369 (19.5%) were 2% or more lower; any LSK minute 6,511 of 42,691 (15.3%).
6 without a 4-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 24 hours
77 of 353 (21.8%) were 2% or more lower; any LSK minute 8,015 of 41,497 (19.3%).
22 without a 24-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 72 hours
44 of 312 (14.1%) were 2% or more lower; any LSK minute 4,520 of 38,617 (11.7%).
63 without a 72-hour close yet, left out.
At least 41 of these windows overlap the rise.
- 7 days
5 of 236 (2.1%) were 2% or more lower; any LSK minute 485 of 32,866 (1.5%).
139 without a 7-day close yet, left out.
At least 74 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 49 of 371 complete windows (13.2%), against 8.0% with no condition (3,453 of 42,900): 1.64x.
Only 371 of the 375 matches have a 30-minute close, and at least 5 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 43 of 374 complete windows; worst point fell 5% or more in 43 of 374.
Picked after the rise, on one market; all 375 matches came from 25 August to 17 September, 5 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 · 11 Sep 21:00 UTC · 8 of 65 stood out
Order book tilt -0.58 or lowerLiquidation 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 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours15-minute price change 0.012 or higher1-hour price change 0.047 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5802 ≤ -0.58 Cascade clustering feature.cascade_clustering_index 0.5831 ≥ 0.58 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 6 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 61 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 6 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 61 12 to 720 Return · 15m feature.ret_15m 0.01234 ≥ 0.012 Return · 1h feature.ret_1h 0.04742 ≥ 0.047 4 hours before · 12 Sep 17:00 UTC · 8 of 65 stood out
4-hour range against usual 3 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 -0.047 or lowerDistance from the day's average price 0.13 or higherShow the full readings
Reading Value at that minute Stored rule Compression · 4h feature.candle_compression_4h 3.049 ≥ 3 Containment · 15m feature.candle_containment_15m inside inside how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 6 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 81 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 6 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 81 12 to 720 Return · 1h feature.ret_1h -0.04792 ≤ -0.047 VWAP distance · day feature.vwap_dist 0.1378 ≥ 0.13 1 hour before · 12 Sep 20:00 UTC · 7 of 65 stood out
Order book lopsidedness 0.049 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 -0.02 or lowerDistance from the day's average price 0.16 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.04851 ≤ 0.049 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 6 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 84 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 6 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 84 12 to 720 Return · 1h feature.ret_1h -0.02013 ≤ -0.02 VWAP distance · day feature.vwap_dist 0.1603 ≥ 0.16 15 minutes before · 12 Sep 20:45 UTC · 8 of 65 stood out
Order book tilt 0.87 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 moreTime since the resistance broke between 12 and 720 hours15-minute price change -0.016 or lower1-hour price change -0.085 or lowerDistance from the day's average price 0.048 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.873 ≥ 0.87 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 6 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 84.75 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 6 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 84.75 12 to 720 Return · 15m feature.ret_15m -0.01619 ≤ -0.016 Return · 1h feature.ret_1h -0.08501 ≤ -0.085 VWAP distance · day feature.vwap_dist 0.04838 ≥ 0.048 1 minute before · 12 Sep 20:59 UTC · 7 of 65 stood out
How 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 hours15-minute price change -0.018 or lower1-hour price change -0.11 or lowerDistance from the day's average price 0.03 or higherShow the full readings
Reading Value at that minute Stored rule how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 6 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 84.98 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 6 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 84.98 12 to 720 Return · 15m feature.ret_15m -0.01812 ≤ -0.018 Return · 1h feature.ret_1h -0.1138 ≤ -0.11 VWAP distance · day feature.vwap_dist 0.03047 ≥ 0.03
Two other reading times we tried 3 and 431 matches
1 minute before (20:59): how many times the broken descending resistance had been tested 3 or higher, how long ago the descending resistance broke between 12 and 720, touches on the broken resistance 3 or more.
how many times the broken descending resistance had been tested ≥ 3 and how long ago the descending resistance broke 12 to 720 and how many times the broken short descending resistance had been tested ≥ 3
3 matches: price was 2% or more higher after 30 minutes in 0 of 3, and 2% or more lower in 0 of 3.
Of the 3 matches, 3 came before the rise began, 0 during it and 0 after it.
15 minutes before (20:45): order book tilt 0.87 or higher, 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 ≥ 0.87 and how many times the broken descending resistance had been tested ≥ 3 and how long ago the descending resistance broke 12 to 720
431 matches: price was 2% or more higher after 30 minutes in 45 of 428 (10.5%), and 2% or more lower in 55 of 428 (12.9%).
Of the first 400 of 431 matches checked, 298 came before the rise began, 5 during it and 97 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 20:00: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market; all 375 matches came from 25 August to 17 September, 5 during the rise.
Hourly candles around the risefull context, lead-up, move
The 21:00 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_crypto, sector_layer_2. 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: 2026-08-19 to 2026-09-18 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.