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-MAKEUSDT rose 338% on 2 September 2026
Picked after the rise, on one market; all matches came within 7 days.
Next stepWhat happened
Price opened the 14:00 hour at 0.01024 and reached a highest trade of 0.04486 in the 21:00 hour; the tested readings were taken at 13:00.
What stood out at 13:00
- Order book lopsidedness0.04788Tested: 0.048 or lower
- Liquidation bunching0.5459Tested: 0.54 or higher
- Touches on the broken resistance4Tested: 3 or more
13:00 always meets its own rules.
What the record says
About as often as any AKE minute
Price at least 2% higher after 30 minutes
111 matches in 9,001 minutes checked.
Picked after the rise, on one market.
Evidence
Does it hold outside that week?
Nothing runs until you press Run.
Exactly what was counted3 conditions · 111 of 9,001 minutes · saved text
- Order book lopsidedness 0.048 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 ≤ 0.048 · feature.book_imbalance_pctrank
- Liquidation bunching 0.54 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.54 · feature.cascade_clustering_index
- Touches on the broken resistance 3 or more. How many times price had touched the falling resistance line that most recently broke.how many times the broken short descending resistance had been tested ≥ 3 · feature.desc_resistance_short_broken_touches
Read at 1 hour before the move.
Read at 13:00 UTC on 2 September, one hour before the selected 14:00 start.
AKE only, 5 August to 3 September 2026 (UTC, ending 4 September 00:00); all 3 readings had values on 9,001 of those minutes.
Reference: every AKE 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 14:00 start was picked automatically after the move.
AKEUSDT stored readings end 2026-09-04 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#99cc1223 @ dataset ea3968f0, counted 5 Sep 2026 07:57 UTC.
Saved summary text, as written 5 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: 111 of the 9,001 minutes searched (1.2%), about 3.6 a day. What followed was more often lower: 63 of the 111 matches with a complete 30 minutes forward fell (57%).
After 72 hours this setup rose 2% or more in 45 of 62 complete windows (72.6%), against 40.7% with no condition (15,836 of 38,881): 1.78x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 19 of its 62 windows overlap the rise.
Best point inside 72 hours reached +5% or more in 55 of 62 complete windows; worst point fell 5% or more in 46 of 62.
At least 39 windows did both.
About 3.6 a day, on 7 of 31 days: spread through the record rather than one event.
These 7 days are in a row, so the matches are closer to one episode than a spread. It counts the single minute on 4 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 7 times in the 43,201 minutes searched. What followed was more often lower: 4 of the 7 matches with a complete 30 minutes forward fell (57%).
3 rose and 4 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 5 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 12 times in the 43,168 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 8 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; all 111 matches came from 28 August to 3 September, 5 during the rise.
When the matches happened7 days in a row
- 28 Aug5 matches
- 29 Aug18 matches
- 30 Aug20 matches
- 31 Aug19 matches
- 1 Sep18 matches
- 2 Sep19 matches
- 3 Sep12 matches
No matches on the other 23 days.
Of the 111 matches, 91 came before the rise began, 5 during it and 15 after it.
Neighbouring minutes overlap, so these are not 111 separate trials.
Picked after the rise, on one market; all 111 matches came from 28 August to 3 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 AKE minute.
- 30 minutes
11 of 111 (9.9%) were 2% or more lower; any AKE minute 3,693 of 43,171 (8.6%).
Every match has a 30-minute close.
At least 5 of these windows overlap the rise.
- 1 hour
14 of 110 (12.7%) were 2% or more lower; any AKE minute 5,579 of 43,141 (12.9%).
1 without a 1-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 4 hours
32 of 108 (29.6%) were 2% or more lower; any AKE minute 11,313 of 42,961 (26.3%).
3 without a 4-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 24 hours
33 of 99 (33.3%) were 2% or more lower; any AKE minute 16,045 of 41,761 (38.4%).
12 without a 24-hour close yet, left out.
At least 16 of these windows overlap the rise.
- 72 hours
14 of 62 (22.6%) were 2% or more lower; any AKE minute 14,931 of 38,881 (38.4%).
49 without a 72-hour close yet, left out.
At least 19 of these windows overlap the rise.
- 7 days
None of the 111 matches has a 7-day close yet, so there is no rate.
Any AKE minute: 16,009 of 33,121 (48.3%) were 2% or more higher, 13,554 of 33,121 (40.9%) lower.
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 72 hours.
After 72 hours this setup rose 2% or more in 45 of 62 complete windows (72.6%), against 40.7% with no condition (15,836 of 38,881): 1.78x.
Only 62 of the 111 matches have a 72-hour close, all from 28 to 31 August, and at least 19 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 72 hours, not the close):
Best point inside 72 hours reached +5% or more in 55 of 62 complete windows; worst point fell 5% or more in 46 of 62.
At least 39 windows did both, so this describes a very jumpy stretch, not a direction.
Picked after the rise, on one market; all 111 matches came from 28 August to 3 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 · 1 Sep 14:00 UTC · 5 of 58 stood out
Order book tilt -0.95 or lower1-hour range against usual 0.36 or lowerLiquidation bunching 0.57 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9595 ≤ -0.95 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3567 ≤ 0.36 Cascade clustering feature.cascade_clustering_index 0.5766 ≥ 0.57 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 92 12 to 720 4 hours before · 2 Sep 10:00 UTC · 9 of 58 stood out
Order book tilt 0.56 or higher1-hour range against usual 3.7 or higher4-hour range against usual 0.5 or lowerLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursVolatility rank 0.98 or higher15-minute price change -0.011 or lower1-hour price change 0.058 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5602 ≥ 0.56 the last one-hour candle range versus its baseline feature.candle_compression_1h 3.727 ≥ 3.7 the last four-hour candle range versus its baseline feature.candle_compression_4h 0.4981 ≤ 0.5 Cascade clustering feature.cascade_clustering_index 0.5469 ≥ 0.54 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 112 12 to 720 Realized vol percentile feature.realized_vol_pctrank 0.9836 ≥ 0.98 Return · 15m feature.ret_15m -0.01146 ≤ -0.011 Return · 1h feature.ret_1h 0.05809 ≥ 0.058 1 hour before · 2 Sep 13:00 UTC · 4 of 58 stood out
Order book lopsidedness 0.048 or lowerLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.04788 ≤ 0.048 Cascade clustering feature.cascade_clustering_index 0.5459 ≥ 0.54 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 115 12 to 720 15 minutes before · 2 Sep 13:45 UTC · 11 of 58 stood out
Order book tilt -0.7 or lowerOrder book lopsidedness 0.06 or lower15-minute range against usual 8.2 or higherLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursOpen interest change rank 0.99 or higherVolatility rank 0.98 or higher15-minute price change 0.09 or higher1-hour price change 0.11 or higherDistance 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 -0.7057 ≤ -0.7 Book imbalance percentile feature.book_imbalance_pctrank 0.0595 ≤ 0.06 Compression · 15m feature.candle_compression_15m 8.202 ≥ 8.2 Cascade clustering feature.cascade_clustering_index 0.5401 ≥ 0.54 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 115.8 12 to 720 OI velocity percentile feature.oi_velocity_pctrank 1 ≥ 0.99 Realized vol percentile feature.realized_vol_pctrank 0.9865 ≥ 0.98 Return · 15m feature.ret_15m 0.09003 ≥ 0.09 Return · 1h feature.ret_1h 0.1101 ≥ 0.11 VWAP distance · day feature.vwap_dist 0.1025 ≥ 0.1 1 minute before · 2 Sep 13:59 UTC · 8 of 58 stood out
15-minute range against usual 8.2 or higherLiquidation bunching 0.54 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursVolatility rank 0.99 or higher15-minute price change 0.066 or higher1-hour price change 0.18 or higherDistance from the day's average price 0.12 or higherShow the full readings
Reading Value at that minute Stored rule Compression · 15m feature.candle_compression_15m 8.202 ≥ 8.2 Cascade clustering feature.cascade_clustering_index 0.5417 ≥ 0.54 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 116 12 to 720 Realized vol percentile feature.realized_vol_pctrank 1 ≥ 0.99 Return · 15m feature.ret_15m 0.06691 ≥ 0.066 Return · 1h feature.ret_1h 0.1824 ≥ 0.18 VWAP distance · day feature.vwap_dist 0.1245 ≥ 0.12
Two other reading times we tried 7 and 12 matches
1 minute before (13:59): 15-minute range against usual 8.2 or higher, liquidation bunching 0.54 or higher, volatility rank 0.99 or higher.
Compression · 15m ≥ 8.2 and Cascade clustering ≥ 0.54 and Realized vol percentile ≥ 0.99
7 matches: price was 2% or more higher after 30 minutes in 3 of 7, and 2% or more lower in 3 of 7.
Of the 7 matches, 6 came before the rise began, 0 during it and 1 after it.
15 minutes before (13:45): order book lopsidedness 0.06 or lower, open interest change rank 0.99 or higher, volatility rank 0.98 or higher.
Book imbalance percentile ≤ 0.06 and OI velocity percentile ≥ 0.99 and Realized vol percentile ≥ 0.98
12 matches: price was 2% or more higher after 30 minutes in 5 of 12, and 2% or more lower in 2 of 12.
Of the 12 matches, 12 came before the rise began, 0 during it and 0 after it.
Fewer than 30 results, so no rate is printed.
The saved study leads with 13:00 because it is the only set with at least 30 matches before the rise.
Picked after the rise, on one market; all 111 matches came from 28 August to 3 September, 5 during the rise.
Charts before and around the rise4-hour structure, hourly candles
The structure before the surge
Price touched a falling resistance 4 times, then an hourly close broke it at 18:00 UTC on 28 August, almost five days before the rise.
4-hour candles up to 13:00 on 2 September; context, not a cause.
Price 0.003989 to 0.0163 USDT
How to read the lines and markers
At 09-02 13:00 UTC, no resistance line was armed. The earlier line had 4 counted touches and broke at 08-28 18:00 UTC, 115 hours before this snapshot. It was not a fresh breakout before the selected move.
Dashed descending line: the earlier resistance. Filled light circles: counted touches. Hollow circles: other swing highs. Dark circles: swing lows. The vertical dotted line marks the earlier break.
Hourly candles around the rise
The 14:00 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 71 sector alpha markets · No result for these markets has been measured.
- Every recorded market
Same 3 conditions on AKE, 6 July to 4 August 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.