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-MHFTUSDT rose 422% on 3 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 21:00 hour at 0.00843 and reached a highest trade of 0.04402 in the 08:00 hour; the tested readings were taken at 20:59.
What stood out at 20:59
- Containment (15m)insideTested: is inside
- Liquidation bunching0.5395Tested: 0.53 or higher
- Distance from the day's average price0.02032Tested: 0.02 or higher
20:59 always meets its own rules.
What the record says
No counts were saved to compare, only the summary text
Picked after the rise, on one market.
Evidence
Does it hold on other dates?
Nothing runs until you press Run.
Exactly what was counted3 conditions · 49 of 41,761 minutes · saved text
Saved summary text, as written 10 Aug 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 49 times in the 41,761 minutes searched (0.1%). What followed was close to a coin flip: 22 rose and 25 fell over the next 30 minutes (47 of the 49 matches have a complete 30 minutes forward).
About 1.6 a day, on 13 of 31 days: spread through the record rather than one event.
The other reading times, as written
From 15 minutes before
Minutes like this appeared only 11 times in the 41,761 minutes searched. What followed leaned up: 7 of the 11 matches with a complete 30 minutes forward rose (64%).
About 0.4 a day, on 8 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 10 times in the 41,761 minutes searched. What followed leaned up: 6 of the 8 matches with a complete 30 minutes forward rose (75%).
About 0.3 a day, on 9 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market.
- Containment (15m) is inside.Containment · 15m inside · feature.candle_containment_15m
- Liquidation bunching 0.53 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.53 · feature.cascade_clustering_index
- Distance from the day's average price 0.02 or higher. How far price sat above or below the day's volume weighted average, as a fraction of it.VWAP distance · day ≥ 0.02 · feature.vwap_dist
Read at 1 minute before the move.
Read at 20:59 UTC on 3 August, one minute before the selected 21:00 start.
HFT only, 10 July to 8 August 2026 (UTC, ending 9 August 00:00); all 3 readings had values on 41,761 of those minutes.
Reference: every HFT 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 21:00 start was picked automatically after the move.
HFTUSDT stored readings end 2026-08-09 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#60042432 @ dataset 34c2a990, counted 10 Aug 2026 02:54 UTC.
When the matches happened
Of the 49 matches, 18 came before the rise began, 31 during it and 0 after it.
Neighbouring minutes overlap, so these are not 49 separate trials.
Picked after the rise, on one market.
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 · 2 Aug 21:00 UTC · 3 of 39 stood out
Order book tilt 0.83 or higher15-minute range against usual 0.33 or lowerLiquidation bunching 0.52 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8383 ≥ 0.83 Compression · 15m feature.candle_compression_15m 0.3288 ≤ 0.33 Cascade clustering feature.cascade_clustering_index 0.5275 ≥ 0.52 4 hours before · 3 Aug 17:00 UTC · 5 of 39 stood out
Order book tilt 0.74 or higherLiquidation bunching 0.53 or higher15-minute price change -0.03 or lower1-hour price change -0.11 or lowerDistance from the day's average price 0.073 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.7425 ≥ 0.74 Cascade clustering feature.cascade_clustering_index 0.5381 ≥ 0.53 Return · 15m feature.ret_15m -0.03074 ≤ -0.03 Return · 1h feature.ret_1h -0.1143 ≤ -0.11 VWAP distance · day feature.vwap_dist 0.07328 ≥ 0.073 1 hour before · 3 Aug 20:00 UTC · 6 of 39 stood out
15-minute range against usual 0.5 or lowerContainment (15m) is insideLower wick (15m) 0.66 or higherLiquidation bunching 0.53 or higherTaker buy share (15m) 0.68 or higherDistance from the day's average price 0.026 or higherShow the full readings
Reading Value at that minute Stored rule Compression · 15m feature.candle_compression_15m 0.4909 ≤ 0.5 Containment · 15m feature.candle_containment_15m inside inside Lower wick · 15m feature.candle_lower_wick_15m 0.6667 ≥ 0.66 Cascade clustering feature.cascade_clustering_index 0.5395 ≥ 0.53 Taker buy share · 15m feature.taker_buy_ratio_15m 0.6857 ≥ 0.68 VWAP distance · day feature.vwap_dist 0.02657 ≥ 0.026 15 minutes before · 3 Aug 20:45 UTC · 5 of 39 stood out
Order book tilt -0.53 or lowerOrder book lopsidedness 0.047 or lowerContainment (15m) is insideLiquidation bunching 0.53 or higherDistance from the day's average price 0.027 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5339 ≤ -0.53 Book imbalance percentile feature.book_imbalance_pctrank 0.04696 ≤ 0.047 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5395 ≥ 0.53 VWAP distance · day feature.vwap_dist 0.02761 ≥ 0.027 1 minute before · 3 Aug 20:59 UTC · 3 of 39 stood out
Containment (15m) is insideLiquidation bunching 0.53 or higherDistance from the day's average price 0.02 or higherShow the full readings
Reading Value at that minute Stored rule Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5395 ≥ 0.53 VWAP distance · day feature.vwap_dist 0.02032 ≥ 0.02
Two other reading times we tried 11 and 10 matches
15 minutes before (20:45): order book tilt -0.53 or lower, order book lopsidedness 0.047 or lower, containment (15m) is inside.
Book imbalance · top levels ≤ -0.53 and Book imbalance percentile ≤ 0.047 and Containment · 15m inside
11 matches.
Of the 11 matches, 7 came before the rise began, 4 during it and 0 after it.
1 hour before (20:00): 15-minute range against usual 0.5 or lower, containment (15m) is inside, lower wick (15m) 0.66 or higher.
Compression · 15m ≤ 0.5 and Containment · 15m inside and Lower wick · 15m ≥ 0.66
10 matches.
Of the 10 matches, 10 came before the rise began, 0 during it and 0 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.
Hourly candles around the risefull context, lead-up, move
The 21:00 start was picked after the move.
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
Same 3 conditions on HFT, 10 June to 9 July 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.