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-MBTWUSDT rose 94% on 1 September 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 13:00 hour at 0.3898 and reached a highest trade of 0.7564 in the 21:00 hour; the tested readings were taken at 12:45.
What stood out at 12:45
- Order book tilt-0.8045Tested: -0.8 or lower
- 15-minute range against usual0.4698Tested: 0.47 or lower
- 1-hour range against usual0.3526Tested: 0.36 or lower
12:45 always meets its own rules.
What the record says
Too few results to compare
Price at least 2% higher after 30 minutes
22 matches in 43,201 minutes checked.
Picked after the rise, on one market.
Evidence
Does it hold on more dates?
Nothing runs until you press Run.
Exactly what was counted3 conditions · 22 of 43,201 minutes · saved text
- Order book tilt -0.8 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.8 · feature.book_imbalance
- 15-minute range against usual 0.47 or lower. The last finished 15-minute candle's high to low range, as a multiple of its usual range.Compression · 15m ≤ 0.47 · feature.candle_compression_15m
- 1-hour range against usual 0.36 or lower. The last finished 1-hour candle's high to low range, as a multiple of its usual range.the last one-hour candle range versus its baseline ≤ 0.36 · feature.candle_compression_1h
Read at 15 minutes before the move.
Read at 12:45 UTC on 1 September, 15 minutes before the selected 13:00 start.
BTW only, 5 August to 3 September 2026 (UTC, ending 4 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every BTW 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 13:00 start was picked automatically after the move.
BTWUSDT 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#53b88315 @ 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 appeared only 22 times in the 43,201 minutes searched. What followed was more often higher: 13 of the 22 matches with a complete 30 minutes forward rose (59%).
13 rose and 9 fell over 22 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 0.7 a day, on 14 of 31 days: spread through the record rather than one event.
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 13 times in the 43,201 minutes searched. What followed was more often higher: 10 of the 13 matches with a complete 30 minutes forward rose (77%).
10 rose and 3 fell over 13 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 10 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 13 times in the 43,201 minutes searched. What followed was close to a coin flip: 7 rose and 6 fell over the next 30 minutes (13 of the 13 matches have a complete 30 minutes forward).
7 rose and 6 fell over 13 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 10 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 22 matches came on 14 of 30 days.
When the matches happened14 of 30 days
- 8 Aug1 match
- 9 Aug1 match
- 13 Aug2 matches
- 14 Aug2 matches
- 16 Aug1 match
- 17 Aug1 match
- 18 Aug1 match
- 20 Aug1 match
- 26 Aug1 match
- 27 Aug1 match
- 29 Aug2 matches
- 30 Aug4 matches
- 1 Sep1 match
- 3 Sep3 matches
No matches on the other 16 days.
Of the 22 matches, 19 came before the rise began, 0 during it and 3 after it.
Neighbouring minutes overlap, so these are not 22 separate trials.
Picked after the rise, on one market; the 22 matches came on 14 of 30 days.
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 BTW minute.
- 30 minutes
3 of 22 were 2% or more lower; any BTW minute 5,166 of 43,171 (12.0%).
Every match has a 30-minute close.
- 1 hour
4 of 22 were 2% or more lower; any BTW minute 6,720 of 43,141 (15.6%).
Every match has a 1-hour close.
- 4 hours
5 of 22 were 2% or more lower; any BTW minute 9,543 of 42,961 (22.2%).
Every match has a 4-hour close.
- 24 hours
3 of 19 were 2% or more lower; any BTW minute 12,399 of 41,761 (29.7%).
3 without a 24-hour close yet, left out.
- 72 hours
2 of 18 were 2% or more lower; any BTW minute 9,661 of 38,881 (24.8%).
4 without a 72-hour close yet, left out.
At least 4 of these windows overlap the rise.
- 7 days
0 of 12 were 2% or more lower; any BTW minute 7,509 of 33,121 (22.7%).
10 without a 7-day close yet, left out.
At least 2 of these windows overlap the rise.
Picked after the rise, on one market; the 22 matches came on 14 of 30 days.
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 · 31 Aug 13:00 UTC · 5 of 58 stood out
Order book tilt -0.93 or lower4-hour range against usual 0.26 or lowerLower wick (15m) 0.74 or higherSweep + reclaim (15m) is bullishLiquidation bunching 0.55 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9323 ≤ -0.93 the last four-hour candle range versus its baseline feature.candle_compression_4h 0.2572 ≤ 0.26 Lower wick · 15m feature.candle_lower_wick_15m 0.7424 ≥ 0.74 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.5517 ≥ 0.55 4 hours before · 1 Sep 09:00 UTC · 6 of 58 stood out
1-hour range against usual 0.45 or lower4-hour range against usual 2.2 or higherEngulfing (1h) is bearishSweep + reclaim (1h) is bullishLiquidation bunching 0.56 or higherDistance from the day's average price -0.063 or lowerShow the full readings
Reading Value at that minute Stored rule the last one-hour candle range versus its baseline feature.candle_compression_1h 0.4412 ≤ 0.45 the last four-hour candle range versus its baseline feature.candle_compression_4h 2.276 ≥ 2.2 Engulfing · 1h feature.candle_engulfing_1h bearish bearish Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bullish bullish Cascade clustering feature.cascade_clustering_index 0.5666 ≥ 0.56 VWAP distance · day feature.vwap_dist -0.06389 ≤ -0.063 1 hour before · 1 Sep 12:00 UTC · 6 of 58 stood out
15-minute range against usual 0.4 or lower1-hour range against usual 0.36 or lowerContainment (15m) is insideUpper wick (15m) 0.61 or higherLiquidation bunching 0.56 or higherDistance from the day's average price -0.047 or lowerShow the full readings
Reading Value at that minute Stored rule Compression · 15m feature.candle_compression_15m 0.3998 ≤ 0.4 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3526 ≤ 0.36 Containment · 15m feature.candle_containment_15m inside inside Upper wick · 15m feature.candle_upper_wick_15m 0.6121 ≥ 0.61 Cascade clustering feature.cascade_clustering_index 0.568 ≥ 0.56 VWAP distance · day feature.vwap_dist -0.0477 ≤ -0.047 15 minutes before · 1 Sep 12:45 UTC · 6 of 58 stood out
Order book tilt -0.8 or lower15-minute range against usual 0.47 or lower1-hour range against usual 0.36 or lowerContainment (15m) is insideLiquidation bunching 0.56 or higherDistance from the day's average price -0.046 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.8045 ≤ -0.8 Compression · 15m feature.candle_compression_15m 0.4698 ≤ 0.47 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3526 ≤ 0.36 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.568 ≥ 0.56 VWAP distance · day feature.vwap_dist -0.04655 ≤ -0.046 1 minute before · 1 Sep 12:59 UTC · 7 of 58 stood out
Order book tilt -0.95 or lowerOrder book lopsidedness 0.061 or lower15-minute range against usual 0.47 or lower1-hour range against usual 0.36 or lowerContainment (15m) is insideLiquidation bunching 0.56 or higherDistance from the day's average price -0.045 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9595 ≤ -0.95 Book imbalance percentile feature.book_imbalance_pctrank 0.06072 ≤ 0.061 Compression · 15m feature.candle_compression_15m 0.4698 ≤ 0.47 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3526 ≤ 0.36 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.568 ≥ 0.56 VWAP distance · day feature.vwap_dist -0.04596 ≤ -0.045
Two other reading times we tried 13 and 13 matches
1 minute before (12:59): order book tilt -0.95 or lower, order book lopsidedness 0.061 or lower, 15-minute range against usual 0.47 or lower.
Book imbalance · top levels ≤ -0.95 and Book imbalance percentile ≤ 0.061 and Compression · 15m ≤ 0.47
13 matches: price was 2% or more higher after 30 minutes in 0 of 13, and 2% or more lower in 1 of 13.
Of the 13 matches, 11 came before the rise began, 1 during it and 1 after it.
1 hour before (12:00): 15-minute range against usual 0.4 or lower, 1-hour range against usual 0.36 or lower, containment (15m) is inside.
Compression · 15m ≤ 0.4 and the last one-hour candle range versus its baseline ≤ 0.36 and Containment · 15m inside
13 matches: price was 2% or more higher after 30 minutes in 1 of 13, and 2% or more lower in 1 of 13.
Of the 13 matches, 12 came before the rise began, 0 during it and 1 after it.
Fewer than 30 results, so no rate is printed.
No set had 30 matches before the rise; the saved study leads with the one that had the most.
Picked after the rise, on one market; the 22 matches came on 14 of 30 days.
Hourly candles around the risefull context, lead-up, move
The 13:00 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 467 small cap markets · No result for these markets has been measured.
- Every recorded market
Same 3 conditions on BTW, 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.