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-MCELRUSDT rose 145% on 18 September 2026
Picked after the rise, on one market; all matches came within 30 days.
What happened
Price opened the 00:00 hour at 0.002134 and reached a highest trade of 0.00523 in the 05:00 hour; the tested readings were taken at 23:00.
What stood out at 23:00
- Order book tilt-0.9109Tested: -0.91 or lower
- Book capturenativeTested: is native
- Containment (15m)outsideTested: is outside
23:00 always meets its own rules.
What the record says
More often than any CELR minute, in this sample
Price at least 2% higher after 30 minutes
106 matches in 43,201 minutes checked; 1 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 · 106 of 43,201 minutes · saved text
- Order book tilt -0.91 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.91 · feature.book_imbalance
- Book capture is native.Book capture native · feature.book_source
- Containment (15m) is outside.Containment · 15m outside · feature.candle_containment_15m
Read at 1 hour before the move.
Read at 23:00 UTC on 17 September, one hour before the selected 00:00 start.
CELR only, 23 August to 21 September 2026 (UTC, ending 22 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every CELR 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 00:00 start was picked automatically after the move.
CELRUSDT stored readings end 2026-09-22 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#03fb33e8 @ dataset 85fdc316, counted 22 Sep 2026 08:33 UTC.
Saved summary text, as written 22 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 106 times in the 43,201 minutes searched (0.2%). What followed was close to a coin flip: 54 rose and 51 fell over the next 30 minutes (105 of the 106 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 1 of 105 complete windows (1.0%), against 2.2% with no condition (904 of 42,010): 0.44x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 12 of its 105 windows overlap the rise.
Best point inside 30 minutes reached +5% or more in 4 of 106 complete windows; worst point fell 5% or more in 0 of 106.
About 3.4 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 22 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 13 times in the 43,201 minutes searched. What followed was more often higher: 7 of the 12 matches with a complete 30 minutes forward rose (58%).
7 rose and 5 fell over 12 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 0.4 a day, on 11 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 12 times in the 43,201 minutes searched. What followed was more often higher: 7 of the 12 matches with a complete 30 minutes forward rose (58%).
7 rose and 5 fell over 12 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 0.4 a day, on 12 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; all 106 matches came from 23 August to 21 September, 12 during the rise.
When the matches happened30 days in a row
- 23 Aug5 matches
- 24 Aug3 matches
- 25 Aug3 matches
- 26 Aug2 matches
- 27 Aug5 matches
- 28 Aug4 matches
- 29 Aug4 matches
- 30 Aug6 matches
- 31 Aug3 matches
- 1 Sep4 matches
- 2 Sep3 matches
- 3 Sep2 matches
- 4 Sep2 matches
- 5 Sep3 matches
- 6 Sep3 matches
- 7 Sep4 matches
- 8 Sep3 matches
- 9 Sep3 matches
- 10 Sep3 matches
- 11 Sep3 matches
- 12 Sep5 matches
- 13 Sep3 matches
- 14 Sep5 matches
- 15 Sep1 match
- 16 Sep1 match
- 17 Sep6 matches
- 18 Sep5 matches
- 19 Sep5 matches
- 20 Sep5 matches
- 21 Sep2 matches
Of the 106 matches, 89 came before the rise began, 12 during it and 5 after it.
Neighbouring minutes overlap, so these are not 106 separate trials.
Picked after the rise, on one market; all 106 matches came from 23 August to 21 September, 12 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 CELR minute.
- 30 minutes
1 of 105 (1.0%) was 2% or more lower; any CELR minute 904 of 42,010 (2.2%).
1 without a 30-minute close yet, left out.
At least 12 of these windows overlap the rise.
- 1 hour
4 of 105 (3.8%) were 2% or more lower; any CELR minute 1,527 of 41,987 (3.6%).
1 without a 1-hour close yet, left out.
At least 12 of these windows overlap the rise.
- 4 hours
11 of 102 (10.8%) were 2% or more lower; any CELR minute 4,220 of 41,799 (10.1%).
4 without a 4-hour close yet, left out.
At least 12 of these windows overlap the rise.
- 24 hours
32 of 103 (31.1%) were 2% or more lower; any CELR minute 12,108 of 40,619 (29.8%).
3 without a 24-hour close yet, left out.
At least 12 of these windows overlap the rise.
- 72 hours
36 of 93 (38.7%) were 2% or more lower; any CELR minute 13,292 of 37,757 (35.2%).
13 without a 72-hour close yet, left out.
At least 7 of these windows overlap the rise.
- 7 days
47 of 81 (58.0%) were 2% or more lower; any CELR minute 19,645 of 32,102 (61.2%).
25 without a 7-day close yet, left out.
At least 13 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 1 of 105 complete windows (1.0%), against 2.2% with no condition (904 of 42,010): 0.44x.
Only 105 of the 106 matches have a 30-minute close, and at least 12 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 106 complete windows; worst point fell 5% or more in 0 of 106.
Picked after the rise, on one market; all 106 matches came from 23 August to 21 September, 12 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 · 17 Sep 00:00 UTC · 12 of 87 stood out
Book capture is native1-hour range against usual 2 or higherSweep + reclaim (15m) is bearishLiquidation bunching 0.53 or higherDepth capture is liveHow 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 hoursMinutes to funding 1 or lower1-hour price change 0.024 or higherTaker buy share (15m) 0.68 or higherShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Compression · 1h feature.candle_compression_1h 2.02 ≥ 2 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5363 ≥ 0.53 Depth capture feature.depth_source live live 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 324 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 179 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 Return · 1h feature.ret_1h 0.02414 ≥ 0.024 Taker buy share · 15m feature.taker_buy_ratio_15m 0.686 ≥ 0.68 4 hours before · 17 Sep 20:00 UTC · 11 of 87 stood out
Order book tilt 0.6 or higherBook capture is nativeUpper wick (15m) 0.78 or higherLiquidation bunching 0.53 or higherDepth capture is liveHow 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 hoursTaker buy share (15m) 0.32 or lowerDistance from the day's average price 0.029 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.6058 ≥ 0.6 Book capture feature.book_source native native Upper wick · 15m feature.candle_upper_wick_15m 0.7857 ≥ 0.78 Cascade clustering feature.cascade_clustering_index 0.5348 ≥ 0.53 Depth capture feature.depth_source live live 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 344 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 199 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.3165 ≤ 0.32 VWAP distance · day feature.vwap_dist 0.02961 ≥ 0.029 1 hour before · 17 Sep 23:00 UTC · 11 of 87 stood out
Order book tilt -0.91 or lowerBook capture is nativeContainment (15m) is outsideEngulfing (15m) is bearishLiquidation bunching 0.53 or higherDepth capture is liveHow 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 higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9109 ≤ -0.91 Book capture feature.book_source native native Containment · 15m feature.candle_containment_15m outside outside Engulfing · 15m feature.candle_engulfing_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5348 ≥ 0.53 Depth capture feature.depth_source live live 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 347 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 202 12 to 720 VWAP distance · day feature.vwap_dist 0.02295 ≥ 0.022 15 minutes before · 17 Sep 23:45 UTC · 12 of 87 stood out
Order book lopsidedness 0.039 or lowerBook capture is native15-minute range against usual 0.39 or lowerLower wick (15m) 0.6 or higherLiquidation bunching 0.53 or higherDepth capture is liveHow 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 hoursMinutes to funding 15 or lowerDistance from the day's average price 0.024 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.03834 ≤ 0.039 Book capture feature.book_source native native Compression · 15m feature.candle_compression_15m 0.3846 ≤ 0.39 Lower wick · 15m feature.candle_lower_wick_15m 0.6 ≥ 0.6 Cascade clustering feature.cascade_clustering_index 0.5348 ≥ 0.53 Depth capture feature.depth_source live live 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 347.8 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 202.8 12 to 720 Minutes to funding feature.mins_to_funding 15 ≤ 15 VWAP distance · day feature.vwap_dist 0.0246 ≥ 0.024 1 minute before · 17 Sep 23:59 UTC · 11 of 87 stood out
Book capture is native15-minute range against usual 0.39 or lowerLower wick (15m) 0.6 or higherLiquidation bunching 0.53 or higherDepth capture is liveHow 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 hoursMinutes to funding 1 or lowerDistance from the day's average price 0.023 or higherShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Compression · 15m feature.candle_compression_15m 0.3846 ≤ 0.39 Lower wick · 15m feature.candle_lower_wick_15m 0.6 ≥ 0.6 Cascade clustering feature.cascade_clustering_index 0.5348 ≥ 0.53 Depth capture feature.depth_source live live 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 348 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 203 12 to 720 Minutes to funding feature.mins_to_funding 1 ≤ 1 VWAP distance · day feature.vwap_dist 0.0231 ≥ 0.023
Two other reading times we tried 13 and 12 matches
1 minute before (23:59): book capture is native, 15-minute range against usual 0.39 or lower, lower wick (15m) 0.6 or higher.
Book capture native and Compression · 15m ≤ 0.39 and Lower wick · 15m ≥ 0.6
13 matches: price was 2% or more higher after 30 minutes in 0 of 12, and 2% or more lower in 1 of 12.
Of the 13 matches, 11 came before the rise began, 1 during it and 1 after it.
15 minutes before (23:45): order book lopsidedness 0.039 or lower, book capture is native, 15-minute range against usual 0.39 or lower.
Book imbalance percentile ≤ 0.039 and Book capture native and Compression · 15m ≤ 0.39
12 matches: price was 2% or more higher after 30 minutes in 1 of 12, and 2% or more lower in 0 of 12.
Of the 12 matches, 9 came before the rise began, 1 during it and 2 after it.
Fewer than 30 results, so no rate is printed.
The saved study leads with 23:00 because it is the only set with at least 30 matches before the rise.
Picked after the rise, on one market; all 106 matches came from 23 August to 21 September, 12 during the rise.
Hourly candles around the risefull context, lead-up, move
The 00:00 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: 2026-08-23 to 2026-09-22 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.