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-MGUSDT rose 146% on 16 September 2026
Picked after the rise, on one market; all matches came within 30 days.
What happened
Price opened the 20:00 hour at 0.004137 and reached a highest trade of 0.01019 in the 14:00 hour; the tested readings were taken at 19:45.
What stood out at 19:45
- Order book tilt0.5219Tested: 0.52 or higher
- Order book lopsidedness0.9218Tested: 0.92 or higher
- Book capturenativeTested: is native
19:45 always meets its own rules.
What the record says
About as often as any G minute
Price at least 2% higher after 30 minutes
306 matches in 43,201 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_infrastructure. Choose one explicitly.
Exactly what was counted3 conditions · 306 of 43,201 minutes · saved text
- Order book tilt 0.52 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.52 · feature.book_imbalance
- Order book lopsidedness 0.92 or higher. How lopsided the sizes at the best bid and ask were, either way, against recent readings; low means unusually even.Book imbalance percentile ≥ 0.92 · feature.book_imbalance_pctrank
- Book capture is native.Book capture native · feature.book_source
Read at 15 minutes before the move.
Read at 19:45 UTC on 16 September, 15 minutes before the selected 20:00 start.
G 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 G 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.
GUSDT 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#639b2324 @ 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 are common here: 306 of the 43,201 minutes searched (0.7%), about 9.9 a day. What followed was more often higher: 167 of the 302 matches with a complete 30 minutes forward rose (55%).
After 7 days this setup rose 2% or more in 133 of 232 complete windows (57.3%), against 48.1% with no condition (15,398 of 32,044): 1.19x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 64 of its 232 windows overlap the rise.
Best point inside 7 days reached +5% or more in 174 of 233 complete windows; worst point fell 5% or more in 131 of 233.
At least 72 windows did both.
About 9.9 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 2 times in the 43,201 minutes searched. What followed was more often higher: 2 of the 2 matches with a complete 30 minutes forward rose (100%).
2 rose and 0 fell over 2 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 over 31 days, but 2026-09-15 alone holds 50% of them: this is close to a single episode.
From 24 hours before
Minutes like this appeared only 1 time in the 43,201 minutes searched. What followed was more often higher: 1 of the 1 matches with a complete 30 minutes forward rose (100%).
1 rose and 0 fell over 1 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 a day over 31 days, but 2026-09-15 alone holds 100% of them: this is close to a single episode.
Picked after the rise, on one market; all 306 matches came from 23 August to 21 September, 26 during the rise.
When the matches happened30 days in a row
- 23 Aug4 matches
- 24 Aug6 matches
- 25 Aug14 matches
- 26 Aug10 matches
- 27 Aug13 matches
- 28 Aug6 matches
- 29 Aug14 matches
- 30 Aug13 matches
- 31 Aug10 matches
- 1 Sep12 matches
- 2 Sep9 matches
- 3 Sep7 matches
- 4 Sep11 matches
- 5 Sep12 matches
- 6 Sep5 matches
- 7 Sep5 matches
- 8 Sep6 matches
- 9 Sep15 matches
- 10 Sep15 matches
- 11 Sep13 matches
- 12 Sep12 matches
- 13 Sep13 matches
- 14 Sep11 matches
- 15 Sep12 matches
- 16 Sep9 matches
- 17 Sep14 matches
- 18 Sep15 matches
- 19 Sep11 matches
- 20 Sep8 matches
- 21 Sep1 match
Of the 306 matches, 254 came before the rise began, 26 during it and 26 after it.
Neighbouring minutes overlap, so these are not 306 separate trials.
Picked after the rise, on one market; all 306 matches came from 23 August to 21 September, 26 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 G minute.
- 30 minutes
11 of 302 (3.6%) were 2% or more lower; any G minute 1,621 of 41,929 (3.9%).
4 without a 30-minute close yet, left out.
At least 26 of these windows overlap the rise.
- 1 hour
14 of 297 (4.7%) were 2% or more lower; any G minute 2,335 of 41,901 (5.6%).
9 without a 1-hour close yet, left out.
At least 26 of these windows overlap the rise.
- 4 hours
33 of 297 (11.1%) were 2% or more lower; any G minute 4,416 of 41,716 (10.6%).
9 without a 4-hour close yet, left out.
At least 26 of these windows overlap the rise.
- 24 hours
53 of 299 (17.7%) were 2% or more lower; any G minute 7,446 of 40,498 (18.4%).
7 without a 24-hour close yet, left out.
At least 26 of these windows overlap the rise.
- 72 hours
69 of 278 (24.8%) were 2% or more lower; any G minute 9,757 of 37,655 (25.9%).
28 without a 72-hour close yet, left out.
At least 49 of these windows overlap the rise.
- 7 days
79 of 232 (34.1%) were 2% or more lower; any G minute 12,507 of 32,044 (39.0%).
74 without a 7-day close yet, left out.
At least 64 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 rose 2% or more in 133 of 232 complete windows (57.3%), against 48.1% with no condition (15,398 of 32,044): 1.19x.
Only 232 of the 306 matches have a 7-day close, and at least 64 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 174 of 233 complete windows; worst point fell 5% or more in 131 of 233.
At least 72 windows did both, so this describes a very jumpy stretch, not a direction.
Picked after the rise, on one market; all 306 matches came from 23 August to 21 September, 26 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 · 15 Sep 20:00 UTC · 15 of 87 stood out
Order book tilt -0.98 or lowerOrder book lopsidedness 0.94 or higherBook capture is native1-hour range against usual 4 or higher4-hour range against usual 4.7 or higherContainment (15m) is insideSweep + reclaim (1h) is bearishLiquidation bunching 0.71 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 hoursVolatility rank 0.99 or higherDistance from the day's average price 0.026 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.988 ≤ -0.98 Book imbalance percentile feature.book_imbalance_pctrank 0.9402 ≥ 0.94 Book capture feature.book_source native native Compression · 1h feature.candle_compression_1h 4.035 ≥ 4 Compression · 4h feature.candle_compression_4h 4.739 ≥ 4.7 Containment · 15m feature.candle_containment_15m inside inside Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.7118 ≥ 0.71 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 293 12 to 720 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 92 12 to 720 Realized vol percentile feature.realized_vol_pctrank 0.9994 ≥ 0.99 VWAP distance · day feature.vwap_dist 0.02653 ≥ 0.026 4 hours before · 16 Sep 16:00 UTC · 9 of 87 stood out
Book capture is nativeLiquidation bunching 0.72 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 lowerShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Cascade clustering feature.cascade_clustering_index 0.7239 ≥ 0.72 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 313 12 to 720 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 112 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 VWAP distance · day feature.vwap_dist -0.02374 ≤ -0.023 1 hour before · 16 Sep 19:00 UTC · 8 of 87 stood out
Book capture is nativeLiquidation bunching 0.72 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 lowerShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Cascade clustering feature.cascade_clustering_index 0.7208 ≥ 0.72 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 316 12 to 720 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 115 12 to 720 VWAP distance · day feature.vwap_dist -0.0228 ≤ -0.022 15 minutes before · 16 Sep 19:45 UTC · 9 of 87 stood out
Order book tilt 0.52 or higherOrder book lopsidedness 0.92 or higherBook capture is nativeLiquidation bunching 0.72 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 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5219 ≥ 0.52 Book imbalance percentile feature.book_imbalance_pctrank 0.9218 ≥ 0.92 Book capture feature.book_source native native Cascade clustering feature.cascade_clustering_index 0.7201 ≥ 0.72 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 316.8 12 to 720 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 115.8 12 to 720 1 minute before · 16 Sep 19:59 UTC · 8 of 87 stood out
Book capture is nativeLiquidation bunching 0.72 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) 0.35 or lowerShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Cascade clustering feature.cascade_clustering_index 0.7201 ≥ 0.72 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 317 12 to 720 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 116 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.3479 ≤ 0.35
Two other reading times we tried 2 and 1 matches
1 minute before (19:59): book capture is native, liquidation bunching 0.72 or higher, depth capture is live.
Book capture native and Cascade clustering ≥ 0.72 and Depth capture live
2 matches: price was 2% or more higher after 30 minutes in 1 of 2, and 2% or more lower in 0 of 2.
Of the 2 matches, 1 came before the rise began, 1 during it and 0 after it.
24 hours before (20:00): order book tilt -0.98 or lower, order book lopsidedness 0.94 or higher, volatility rank 0.99 or higher.
Book imbalance · top levels ≤ -0.98 and Book imbalance percentile ≥ 0.94 and Realized vol percentile ≥ 0.99
1 match: price was 2% or more higher after 30 minutes in 0 of 1, and 2% or more lower in 0 of 1.
Of the 1 match, 1 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 19:45 because it is the only set with at least 30 matches before the rise.
Picked after the rise, on one market; all 306 matches came from 23 August to 21 September, 26 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
Multiple recorded sectors: sector_crypto, sector_infrastructure. 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.