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-MBNCUSDT rose 95% on 4 September 2026
Picked after the rise, on one market.
What happened
Price opened the 20:00 hour at 3.482 and reached a highest trade of 6.796 in the 08:00 hour; the tested readings were taken at 19:00.
What stood out at 19:00
- Order book tilt0.5319Tested: 0.53 or higher
- 15-minute range against usual2.49Tested: 2.4 or higher
- Liquidation bunching0.597Tested: 0.59 or higher
19:00 always meets its own rules.
What the record says
Less often than any BNC minute, in this sample
Price at least 2% higher after 30 minutes
99 matches in 36,736 minutes checked; 20 missing a 30-minute close, left out.
Picked after the rise, on one market.
Evidence
No test to open
Choose a recorded Binance crypto perpetual market with confirmed instrument classification.
Exactly what was counted3 conditions · 99 of 36,736 minutes · saved text
- Order book tilt 0.53 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.53 · feature.book_imbalance
- 15-minute range against usual 2.4 or higher. The last finished 15-minute candle's high to low range, as a multiple of its usual range.Compression · 15m ≥ 2.4 · feature.candle_compression_15m
- Liquidation bunching 0.59 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.59 · feature.cascade_clustering_index
Read at 1 hour before the move.
Read at 19:00 UTC on 4 September, one hour before the selected 20:00 start.
BNC only, 12 August to 10 September 2026 (UTC, ending 11 September 00:00); all 3 readings had values on 36,736 of those minutes.
Reference: every BNC 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.
BNCUSDT stored readings end 2026-09-11 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#91bfd642 @ dataset d31fb5af, counted 12 Sep 2026 08:01 UTC.
Saved summary text, as written 12 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 99 times in the 36,736 minutes searched (0.3%). What followed was more often lower: 44 of the 79 matches with a complete 30 minutes forward fell (56%).
After 30 minutes this setup fell 2% or more in 5 of 79 complete windows (6.3%), against 3.9% with no condition (883 of 22,699): 1.63x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 20 of its 79 windows overlap the rise.
Best point inside 30 minutes reached +5% or more in 2 of 94 complete windows; worst point fell 5% or more in 4 of 94.
About 3.2 a day, on 24 of 31 days: spread through the record rather than one event.
It counts the single minute on 11 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared 35 times in the 42,376 minutes searched (<0.1%). What followed was close to a coin flip: 13 rose and 12 fell over the next 30 minutes (25 of the 35 matches have a complete 30 minutes forward).
After 4 hours this setup rose 2% or more in 14 of 30 complete windows (46.7%), against 22.2% with no condition (4,895 of 22,003): 2.10x.
About 1.1 a day, on 16 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared 32 times in the 42,376 minutes searched (<0.1%). What followed was more often higher: 13 of the 23 matches with a complete 30 minutes forward rose (57%).
13 rose and 10 fell over 23 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 1 a day, on 16 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 99 matches came on 24 of 30 days, 20 during the rise.
When the matches happened24 of 30 days
- 13 Aug2 matches
- 14 Aug2 matches
- 19 Aug2 matches
- 20 Aug5 matches
- 21 Aug4 matches
- 22 Aug3 matches
- 23 Aug2 matches
- 24 Aug5 matches
- 25 Aug3 matches
- 26 Aug4 matches
- 27 Aug7 matches
- 28 Aug5 matches
- 29 Aug4 matches
- 31 Aug5 matches
- 1 Sep4 matches
- 2 Sep4 matches
- 3 Sep7 matches
- 4 Sep4 matches
- 5 Sep7 matches
- 6 Sep3 matches
- 7 Sep7 matches
- 8 Sep4 matches
- 9 Sep4 matches
- 10 Sep2 matches
No matches on the other 6 days.
Of the 99 matches, 72 came before the rise began, 20 during it and 7 after it.
Neighbouring minutes overlap, so these are not 99 separate trials.
Picked after the rise, on one market; the 99 matches came on 24 of 30 days, 20 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 BNC minute.
- 30 minutes
5 of 79 (6.3%) were 2% or more lower; any BNC minute 883 of 22,699 (3.9%).
20 without a 30-minute close yet, left out.
At least 20 of these windows overlap the rise.
- 1 hour
8 of 73 (11.0%) were 2% or more lower; any BNC minute 1,695 of 22,598 (7.5%).
26 without a 1-hour close yet, left out.
At least 20 of these windows overlap the rise.
- 4 hours
17 of 77 (22.1%) were 2% or more lower; any BNC minute 3,426 of 22,003 (15.6%).
22 without a 4-hour close yet, left out.
At least 20 of these windows overlap the rise.
- 24 hours
15 of 73 (20.5%) were 2% or more lower; any BNC minute 5,236 of 20,751 (25.2%).
26 without a 24-hour close yet, left out.
At least 20 of these windows overlap the rise.
- 72 hours
12 of 67 (17.9%) were 2% or more lower; any BNC minute 3,435 of 18,159 (18.9%).
32 without a 72-hour close yet, left out.
At least 11 of these windows overlap the rise.
- 7 days
14 of 53 (26.4%) were 2% or more lower; any BNC minute 3,270 of 16,054 (20.4%).
46 without a 7-day close yet, left out.
At least 24 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 5 of 79 complete windows (6.3%), against 3.9% with no condition (883 of 22,699): 1.63x.
Only 79 of the 99 matches have a 30-minute close, and at least 20 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 2 of 94 complete windows; worst point fell 5% or more in 4 of 94.
Picked after the rise, on one market; the 99 matches came on 24 of 30 days, 20 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 · 3 Sep 20:00 UTC · 9 of 63 stood out
Order book tilt 0.57 or higher1-hour range against usual 0.4 or lowerContainment (15m) is outsideUpper wick (15m) 0.78 or higherLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursVPIN regime is elevatedDistance from the day's average price 0.021 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5785 ≥ 0.57 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3942 ≤ 0.4 Containment · 15m feature.candle_containment_15m outside outside Upper wick · 15m feature.candle_upper_wick_15m 0.7895 ≥ 0.78 Cascade clustering feature.cascade_clustering_index 0.5942 ≥ 0.59 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 123 12 to 720 VPIN regime feature.vpin_regime elevated elevated VWAP distance · day feature.vwap_dist 0.02103 ≥ 0.021 4 hours before · 4 Sep 16:00 UTC · 12 of 63 stood out
Order book tilt 0.99 or higher1-hour range against usual 2.2 or higherSweep + reclaim (15m) is bearishLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 1 or lowerVolatility rank 0.93 or higher15-minute price change -0.012 or lower1-hour price change 0.04 or higherToxic flow (VPIN) 0.57 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9903 ≥ 0.99 the last one-hour candle range versus its baseline feature.candle_compression_1h 2.211 ≥ 2.2 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5965 ≥ 0.59 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 143 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 Realized vol percentile feature.realized_vol_pctrank 0.9392 ≥ 0.93 Return · 15m feature.ret_15m -0.0126 ≤ -0.012 Return · 1h feature.ret_1h 0.04074 ≥ 0.04 Toxic flow (VPIN) feature.vpin 0.5725 ≥ 0.57 VPIN regime feature.vpin_regime elevated elevated 1 hour before · 4 Sep 19:00 UTC · 9 of 63 stood out
Order book tilt 0.53 or higher15-minute range against usual 2.4 or higherLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours15-minute price change 0.017 or higherTaker buy share (15m) 0.86 or higherToxic flow (VPIN) 0.54 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5319 ≥ 0.53 Compression · 15m feature.candle_compression_15m 2.49 ≥ 2.4 Cascade clustering feature.cascade_clustering_index 0.597 ≥ 0.59 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 146 12 to 720 Return · 15m feature.ret_15m 0.01756 ≥ 0.017 Taker buy share · 15m feature.taker_buy_ratio_15m 0.8608 ≥ 0.86 Toxic flow (VPIN) feature.vpin 0.5409 ≥ 0.54 VPIN regime feature.vpin_regime elevated elevated 15 minutes before · 4 Sep 19:45 UTC · 8 of 63 stood out
Order book tilt 0.96 or higherEngulfing (15m) is bearishLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursTaker buy share (15m) 0.28 or lowerToxic flow (VPIN) 0.51 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9623 ≥ 0.96 Engulfing · 15m feature.candle_engulfing_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.597 ≥ 0.59 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 146.8 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.2728 ≤ 0.28 Toxic flow (VPIN) feature.vpin 0.5142 ≥ 0.51 VPIN regime feature.vpin_regime elevated elevated 1 minute before · 4 Sep 19:59 UTC · 8 of 63 stood out
Order book tilt 0.94 or higherEngulfing (15m) is bearishLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursTaker buy share (15m) 0.82 or higherToxic flow (VPIN) 0.51 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9418 ≥ 0.94 Engulfing · 15m feature.candle_engulfing_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.597 ≥ 0.59 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 147 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.8204 ≥ 0.82 Toxic flow (VPIN) feature.vpin 0.5142 ≥ 0.51 VPIN regime feature.vpin_regime elevated elevated
Two other reading times we tried 35 and 32 matches
1 minute before (19:59): order book tilt 0.94 or higher, engulfing (15m) is bearish, liquidation bunching 0.59 or higher.
Book imbalance · top levels ≥ 0.94 and Engulfing · 15m bearish and Cascade clustering ≥ 0.59
35 matches: price was 2% or more higher after 30 minutes in 3 of 25, and 2% or more lower in 3 of 25.
Of the 35 matches, 19 came before the rise began, 6 during it and 10 after it.
15 minutes before (19:45): order book tilt 0.96 or higher, engulfing (15m) is bearish, liquidation bunching 0.59 or higher.
Book imbalance · top levels ≥ 0.96 and Engulfing · 15m bearish and Cascade clustering ≥ 0.59
32 matches: price was 2% or more higher after 30 minutes in 3 of 23, and 2% or more lower in 3 of 23.
Of the 32 matches, 18 came before the rise began, 5 during it and 9 after it.
Fewer than 30 results, so no rate is printed.
The saved study leads with 19:00 because it is the only set with at least 30 matches before the rise.
Picked after the rise, on one market; the 99 matches came on 24 of 30 days, 20 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
Choose a recorded Binance crypto perpetual market with confirmed instrument classification.
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: 2026-08-12 to 2026-09-11 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.