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 30% on 2 September 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 13:00 hour at 2.849 and reached a highest trade of 3.71 in the 07:00 hour; the tested readings were taken at 12:59.
What stood out at 12:59
- 1-hour range against usual0.3571Tested: 0.36 or lower
- Containment (15m)outsideTested: is outside
- Liquidation bunching0.5976Tested: 0.59 or higher
12:59 always meets its own rules.
What the record says
Too few results to compare
Price at least 2% higher after 30 minutes
36 matches in 41,566 minutes checked; 19 missing a 30-minute close, left out.
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 · 36 of 41,566 minutes · saved text
- 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
- Containment (15m) is outside.Containment · 15m outside · feature.candle_containment_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 minute before the move.
Read at 12:59 UTC on 2 September, one minute before the selected 13:00 start.
BNC only, 9 August to 7 September 2026 (UTC, ending 8 September 00:00); all 3 readings had values on 41,566 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 13:00 start was picked automatically after the move.
BNCUSDT stored readings end 2026-09-08 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#40c5f866 @ dataset cbaead34, counted 8 Sep 2026 08:28 UTC.
Saved summary text, as written 8 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 36 times in the 41,566 minutes searched (<0.1%). What followed was more often lower: 10 of the 17 matches with a complete 30 minutes forward fell (59%).
7 rose and 10 fell over 17 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 1.2 a day, on 16 of 31 days: spread through the record rather than one event.
It counts the single minute on 8 September as a day.
The other reading times, as written
From 15 minutes before
Minutes like this appeared only 2 times in the 37,510 minutes searched. What followed was more often lower: 2 of the 2 matches with a complete 30 minutes forward fell (100%).
0 rose and 2 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 2026-08-19 alone holds 50% of them: this is close to a single episode.
From 1 hour before
Minutes like this appeared only 16 times in the 42,481 minutes searched. What followed was more often lower: 7 of the 9 matches with a complete 30 minutes forward fell (78%).
2 rose and 7 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 0.5 a day, on 11 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 36 matches came on 16 of 30 days, 5 during the rise.
When the matches happened16 of 30 days
- 12 Aug3 matches
- 13 Aug2 matches
- 22 Aug3 matches
- 23 Aug1 match
- 25 Aug2 matches
- 28 Aug2 matches
- 29 Aug2 matches
- 30 Aug1 match
- 31 Aug1 match
- 1 Sep3 matches
- 2 Sep4 matches
- 3 Sep2 matches
- 4 Sep3 matches
- 5 Sep3 matches
- 6 Sep2 matches
- 7 Sep2 matches
No matches on the other 14 days.
Of the 36 matches, 22 came before the rise began, 5 during it and 9 after it.
Neighbouring minutes overlap, so these are not 36 separate trials.
Picked after the rise, on one market; the 36 matches came on 16 of 30 days, 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 BNC minute.
- 30 minutes
0 of 17 were 2% or more lower; any BNC minute 399 of 19,862 (2.0%).
19 without a 30-minute close yet, left out.
At least 5 of these windows overlap the rise.
- 1 hour
0 of 14 were 2% or more lower; any BNC minute 978 of 19,726 (5.0%).
22 without a 1-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 4 hours
0 of 9 were 2% or more lower; any BNC minute 2,406 of 19,169 (12.6%).
27 without a 4-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 24 hours
2 of 16 were 2% or more lower; any BNC minute 3,625 of 18,429 (19.7%).
20 without a 24-hour close yet, left out.
At least 5 of these windows overlap the rise.
- 72 hours
2 of 12 were 2% or more lower; any BNC minute 3,435 of 16,006 (21.5%).
24 without a 72-hour close yet, left out.
At least 9 of these windows overlap the rise.
- 7 days
3 of 6 were 2% or more lower; any BNC minute 3,270 of 14,273 (22.9%).
30 without a 7-day close yet, left out.
At least 6 of these windows overlap the rise.
Picked after the rise, on one market; the 36 matches came on 16 of 30 days, 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 13:00 UTC · 7 of 58 stood out
1-hour range against usual 2 or higherContainment (15m) is insideLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursVolatility rank 0.98 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule the last one-hour candle range versus its baseline feature.candle_compression_1h 2.037 ≥ 2 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5981 ≥ 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 68 12 to 720 Realized vol percentile feature.realized_vol_pctrank 0.9807 ≥ 0.98 VPIN regime feature.vpin_regime elevated elevated 4 hours before · 2 Sep 09:00 UTC · 6 of 58 stood out
1-hour range against usual 2.5 or higherLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursTaker buy share (15m) 0.35 or lowerDistance from the day's average price 0.021 or higherShow the full readings
Reading Value at that minute Stored rule the last one-hour candle range versus its baseline feature.candle_compression_1h 2.53 ≥ 2.5 Cascade clustering feature.cascade_clustering_index 0.5976 ≥ 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 88 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.3496 ≤ 0.35 VWAP distance · day feature.vwap_dist 0.02164 ≥ 0.021 1 hour before · 2 Sep 12:00 UTC · 6 of 58 stood out
Order book tilt -0.81 or lowerOrder book lopsidedness 0.92 or higher1-hour range against usual 0.36 or lowerLiquidation bunching 0.59 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 -0.8118 ≤ -0.81 Book imbalance percentile feature.book_imbalance_pctrank 0.9226 ≥ 0.92 the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3571 ≤ 0.36 Cascade clustering feature.cascade_clustering_index 0.5976 ≥ 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 91 12 to 720 15 minutes before · 2 Sep 12:45 UTC · 8 of 58 stood out
1-hour range against usual 0.36 or lowerContainment (15m) is outsideLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursOpen interest change rank 0.99 or higherTaker buy share (15m) 0.23 or lowerVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3571 ≤ 0.36 Containment · 15m feature.candle_containment_15m outside outside Cascade clustering feature.cascade_clustering_index 0.5976 ≥ 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 91.75 12 to 720 OI velocity percentile feature.oi_velocity_pctrank 0.9975 ≥ 0.99 Taker buy share · 15m feature.taker_buy_ratio_15m 0.2238 ≤ 0.23 VPIN regime feature.vpin_regime elevated elevated 1 minute before · 2 Sep 12:59 UTC · 7 of 58 stood out
1-hour range against usual 0.36 or lowerContainment (15m) is outsideLiquidation bunching 0.59 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursTaker buy share (15m) 0.66 or higherVPIN regime is elevatedShow the full readings
Reading Value at that minute Stored rule the last one-hour candle range versus its baseline feature.candle_compression_1h 0.3571 ≤ 0.36 Containment · 15m feature.candle_containment_15m outside outside Cascade clustering feature.cascade_clustering_index 0.5976 ≥ 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 91.98 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.6693 ≥ 0.66 VPIN regime feature.vpin_regime elevated elevated
Two other reading times we tried 2 and 16 matches
15 minutes before (12:45): 1-hour range against usual 0.36 or lower, containment (15m) is outside, open interest change rank 0.99 or higher.
the last one-hour candle range versus its baseline ≤ 0.36 and Containment · 15m outside and OI velocity percentile ≥ 0.99
2 matches: price was 2% or more higher after 30 minutes in 0 of 2, and 2% or more lower in 0 of 2.
Of the 2 matches, 2 came before the rise began, 0 during it and 0 after it.
1 hour before (12:00): order book tilt -0.81 or lower, order book lopsidedness 0.92 or higher, 1-hour range against usual 0.36 or lower.
Book imbalance · top levels ≤ -0.81 and Book imbalance percentile ≥ 0.92 and the last one-hour candle range versus its baseline ≤ 0.36
16 matches: price was 2% or more higher after 30 minutes in 0 of 9, and 2% or more lower in 0 of 9.
Of the 16 matches, 11 came before the rise began, 3 during it and 2 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 36 matches came on 16 of 30 days, 5 during the rise.
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 190 sector tradfi markets · No result for these markets has been measured.
- Every recorded market
Same 3 conditions on BNC, 10 July to 8 August 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.