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 140% on 17 September 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 14:00 hour at 0.004255 and reached a highest trade of 0.01019 in the 14:00 hour; the tested readings were taken at 13:00.
What stood out at 13:00
- Order book tilt0.958Tested: 0.95 or higher
- Order book lopsidedness0.9449Tested: 0.94 or higher
- Book capturenativeTested: is native
13:00 always meets its own rules.
What the record says
More often than any G minute, in this sample
Price at least 2% higher after 30 minutes
73 matches in 43,201 minutes checked; 2 missing a 30-minute close, left out.
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 · 73 of 43,201 minutes · saved text
- Order book tilt 0.95 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.95 · feature.book_imbalance
- Order book lopsidedness 0.94 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 ≥ 0.94 · feature.book_imbalance_pctrank
- Book capture is native.Book capture native · feature.book_source
Read at 1 hour before the move.
Read at 13:00 UTC on 17 September, one hour before the selected 14:00 start.
G only, 24 August to 22 September 2026 (UTC, ending 23 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 14:00 start was picked automatically after the move.
GUSDT stored readings end 2026-09-23 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#1df405b0 @ dataset cb0cece4, counted 23 Sep 2026 22:43 UTC.
Saved summary text, as written 23 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 73 times in the 43,201 minutes searched (0.2%). What followed was close to a coin flip: 35 rose and 36 fell over the next 30 minutes (71 of the 73 matches have a complete 30 minutes forward).
After 1 hour this setup fell 2% or more in 1 of 72 complete windows (1.4%), against 5.6% with no condition (2,331 of 41,901): 0.25x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 3 of its 72 windows overlap the rise.
Best point inside 1 hour reached +5% or more in 6 of 72 complete windows; worst point fell 5% or more in 1 of 72.
About 2.4 a day, on 25 of 31 days: spread through the record rather than one event.
It counts the single minute on 23 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this are common here: 278 of the 43,201 minutes searched (0.6%), about 9 a day. What followed was close to a coin flip: 147 rose and 124 fell over the next 30 minutes (271 of the 278 matches have a complete 30 minutes forward).
After 1 hour this setup rose 2% or more in 26 of 271 complete windows (9.6%), against 6.9% with no condition (2,892 of 41,901): 1.39x.
About 9 a day, on 30 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 9 times in the 43,201 minutes searched. What followed was more often higher: 5 of the 9 matches with a complete 30 minutes forward rose (56%).
5 rose and 4 fell over 9 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 0.3 a day over 31 days, but 2026-09-17 alone holds 44% of them: this is close to a single episode.
Picked after the rise, on one market; the 73 matches came on 25 of 30 days, 3 during the rise.
When the matches happened25 of 30 days
- 24 Aug1 match
- 25 Aug1 match
- 27 Aug1 match
- 28 Aug2 matches
- 29 Aug4 matches
- 30 Aug5 matches
- 31 Aug2 matches
- 1 Sep5 matches
- 2 Sep2 matches
- 4 Sep3 matches
- 5 Sep6 matches
- 6 Sep1 match
- 8 Sep3 matches
- 9 Sep2 matches
- 10 Sep5 matches
- 11 Sep6 matches
- 12 Sep3 matches
- 13 Sep6 matches
- 14 Sep3 matches
- 15 Sep2 matches
- 16 Sep1 match
- 17 Sep6 matches
- 18 Sep1 match
- 19 Sep1 match
- 20 Sep1 match
No matches on the other 5 days.
Of the 73 matches, 68 came before the rise began, 3 during it and 2 after it.
Neighbouring minutes overlap, so these are not 73 separate trials.
Picked after the rise, on one market; the 73 matches came on 25 of 30 days, 3 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
1 of 71 (1.4%) was 2% or more lower; any G minute 1,633 of 41,929 (3.9%).
2 without a 30-minute close yet, left out.
At least 3 of these windows overlap the rise.
- 1 hour
1 of 72 (1.4%) was 2% or more lower; any G minute 2,331 of 41,901 (5.6%).
1 without a 1-hour close yet, left out.
At least 3 of these windows overlap the rise.
- 4 hours
3 of 70 (4.3%) were 2% or more lower; any G minute 4,428 of 41,716 (10.6%).
3 without a 4-hour close yet, left out.
At least 3 of these windows overlap the rise.
- 24 hours
13 of 72 (18.1%) were 2% or more lower; any G minute 8,691 of 40,510 (21.5%).
1 without a 24-hour close yet, left out.
At least 3 of these windows overlap the rise.
- 72 hours
13 of 69 (18.8%) were 2% or more lower; any G minute 10,702 of 37,691 (28.4%).
4 without a 72-hour close yet, left out.
At least 6 of these windows overlap the rise.
- 7 days
14 of 60 (23.3%) were 2% or more lower; any G minute 11,649 of 32,090 (36.3%).
13 without a 7-day close yet, left out.
At least 20 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 fell 2% or more in 1 of 72 complete windows (1.4%), against 5.6% with no condition (2,331 of 41,901): 0.25x.
Only 72 of the 73 matches have a 1-hour close, and at least 3 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 6 of 72 complete windows; worst point fell 5% or more in 1 of 72.
Picked after the rise, on one market; the 73 matches came on 25 of 30 days, 3 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 · 16 Sep 14:00 UTC · 9 of 88 stood out
Book capture is nativeLower wick (15m) 0.64 or higherSweep + reclaim (15m) is bullishLiquidation 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 capture feature.book_source native native Lower wick · 15m feature.candle_lower_wick_15m 0.6452 ≥ 0.64 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.7258 ≥ 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 311 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 110 12 to 720 4 hours before · 17 Sep 10:00 UTC · 10 of 88 stood out
Order book tilt -0.86 or lowerBook capture is native4-hour range against usual 0.29 or lowerContainment (15m) is outsideLiquidation 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 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.8629 ≤ -0.86 Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 0.2871 ≤ 0.29 Containment · 15m feature.candle_containment_15m outside outside Cascade clustering feature.cascade_clustering_index 0.7182 ≥ 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 331 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 130 12 to 720 1 hour before · 17 Sep 13:00 UTC · 11 of 88 stood out
Order book tilt 0.95 or higherOrder book lopsidedness 0.94 or higherBook capture is native4-hour range against usual 0.33 or lowerLiquidation 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 hoursTaker buy share (15m) 0.2 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.958 ≥ 0.95 Book imbalance percentile feature.book_imbalance_pctrank 0.9449 ≥ 0.94 Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 0.3269 ≤ 0.33 Cascade clustering feature.cascade_clustering_index 0.7182 ≥ 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 334 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 133 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.1925 ≤ 0.2 15 minutes before · 17 Sep 13:45 UTC · 9 of 88 stood out
Book capture is native4-hour range against usual 0.33 or lowerSweep + reclaim (15m) 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 hoursShow the full readings
Reading Value at that minute Stored rule Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 0.3269 ≤ 0.33 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.7176 ≥ 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 334.8 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 133.8 12 to 720 1 minute before · 17 Sep 13:59 UTC · 12 of 88 stood out
Order book tilt 0.54 or higherBook capture is native4-hour range against usual 0.33 or lowerSweep + reclaim (15m) 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 hoursOpen interest change rank 0.91 or higherTaker buy share (15m) 0.3 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5463 ≥ 0.54 Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 0.3269 ≤ 0.33 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.7176 ≥ 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 335 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 134 12 to 720 OI change magnitude score feature.oi_velocity_pctrank 0.9104 ≥ 0.91 Taker buy share · 15m feature.taker_buy_ratio_15m 0.2935 ≤ 0.3
Two other reading times we tried 278 and 9 matches
1 minute before (13:59): order book tilt 0.54 or higher, book capture is native, open interest change rank 0.91 or higher.
Book imbalance · top levels ≥ 0.54 and Book capture native and OI change magnitude score ≥ 0.91
278 matches: price was 2% or more higher after 30 minutes in 17 of 271 (6.3%), and 2% or more lower in 13 of 271 (4.8%).
Of the 278 matches, 216 came before the rise began, 12 during it and 50 after it.
15 minutes before (13:45): book capture is native, 4-hour range against usual 0.33 or lower, sweep + reclaim (15m) is bearish.
Book capture native and Compression · 4h ≤ 0.33 and Sweep + reclaim · 15m bearish
9 matches: price was 2% or more higher after 30 minutes in 2 of 9, and 2% or more lower in 0 of 9.
Of the 9 matches, 4 came before the rise began, 1 during it and 4 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 13:00: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market; the 73 matches came on 25 of 30 days, 3 during the rise.
Hourly candles around the risefull context, lead-up, move
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 539 eligible crypto markets · No result for these markets has been measured.
- Every recorded market
- 520 sector crypto markets
- 59 sector infrastructure 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: 2026-08-24 to 2026-09-23 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.