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-MHEIUSDT rose 439% on 4 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 17:00 hour at 0.1011 and reached a highest trade of 0.545 in the 09:00 hour; the tested readings were taken at 16:00.
What stood out at 16:00
- Order book lopsidedness0.0619Tested: 0.062 or lower
- Open interest change rank0.9476Tested: 0.94 or higher
- Volatility rank0.9537Tested: 0.95 or higher
16:00 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 · 24 of 43,199 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 only 24 times in the 43,199 minutes searched. What followed leaned up: 14 of the 24 matches with a complete 30 minutes forward rose (58%).
About 0.8 a day, on 19 of 31 days: spread through the record rather than one event.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 15 times in the 43,199 minutes searched. What followed was close to a coin flip: 7 rose and 8 fell over the next 30 minutes (15 of the 15 matches have a complete 30 minutes forward).
About 0.5 a day, on 12 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 9 times in the 43,199 minutes searched. What followed leaned up: 5 of the 9 matches with a complete 30 minutes forward rose (56%).
About 0.3 a day, on 8 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market.
- Order book lopsidedness 0.062 or lower. How lopsided the sizes at the best bid and ask were, either way, against recent readings; low means unusually even.Book imbalance percentile ≤ 0.062 · feature.book_imbalance_pctrank
- Open interest change rank 0.94 or higher. How unusual the change in open positions was, opening or closing, on a 0 to 1 scale.OI velocity percentile ≥ 0.94 · feature.oi_velocity_pctrank
- Volatility rank 0.95 or higher. How volatile the last hour was against this market's history, on a 0 to 1 scale.Realized vol percentile ≥ 0.95 · feature.realized_vol_pctrank
Read at 1 hour before the move.
Read at 16:00 UTC on 4 August, one hour before the selected 17:00 start.
HEI only, 10 July to 8 August 2026 (UTC, ending 9 August 00:00); all 3 readings had values on 43,199 of those minutes.
Reference: every HEI 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 17:00 start was picked automatically after the move.
HEIUSDT 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#405384ec @ dataset 34c2a990, counted 10 Aug 2026 02:54 UTC.
When the matches happened
Of the 24 matches, 21 came before the rise began, 2 during it and 1 after it.
Neighbouring minutes overlap, so these are not 24 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 · 3 Aug 17:00 UTC · 2 of 39 stood out
Order book tilt 0.9 or higherLiquidation bunching 0.51 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9049 ≥ 0.9 Cascade clustering feature.cascade_clustering_index 0.5132 ≥ 0.51 4 hours before · 4 Aug 13:00 UTC · 3 of 39 stood out
Order book tilt 0.99 or higherContainment (15m) is insideLiquidation bunching 0.51 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9904 ≥ 0.99 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5125 ≥ 0.51 1 hour before · 4 Aug 16:00 UTC · 9 of 39 stood out
Order book lopsidedness 0.062 or lowerSweep + reclaim (15m) is bearishUpper wick (15m) 0.75 or higherLiquidation bunching 0.51 or higherMinutes to funding 1 or lowerOpen interest change rank 0.94 or higherVolatility rank 0.95 or higher1-hour price change 0.037 or higherDistance from the day's average price 0.068 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.0619 ≤ 0.062 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Upper wick · 15m feature.candle_upper_wick_15m 0.7573 ≥ 0.75 Cascade clustering feature.cascade_clustering_index 0.5121 ≥ 0.51 Minutes to funding feature.mins_to_funding 0 ≤ 1 OI velocity percentile feature.oi_velocity_pctrank 0.9476 ≥ 0.94 Realized vol percentile feature.realized_vol_pctrank 0.9537 ≥ 0.95 Return · 1h feature.ret_1h 0.03725 ≥ 0.037 VWAP distance · day feature.vwap_dist 0.06808 ≥ 0.068 15 minutes before · 4 Aug 16:45 UTC · 6 of 39 stood out
Sweep + reclaim (15m) is bearishUpper wick (15m) 0.72 or higherLiquidation bunching 0.51 or higherOpen interest change rank 0.97 or higherVolatility rank 0.99 or higherDistance from the day's average price 0.05 or higherShow the full readings
Reading Value at that minute Stored rule Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Upper wick · 15m feature.candle_upper_wick_15m 0.728 ≥ 0.72 Cascade clustering feature.cascade_clustering_index 0.5119 ≥ 0.51 OI velocity percentile feature.oi_velocity_pctrank 0.9798 ≥ 0.97 Realized vol percentile feature.realized_vol_pctrank 0.9983 ≥ 0.99 VWAP distance · day feature.vwap_dist 0.05067 ≥ 0.05 1 minute before · 4 Aug 16:59 UTC · 9 of 39 stood out
Order book tilt -0.9 or lowerSweep + reclaim (15m) is bearishUpper wick (15m) 0.72 or higherLiquidation bunching 0.51 or higherOpen interest change rank 0.93 or higherVolatility rank 0.99 or higher15-minute price change 0.028 or higher1-hour price change 0.038 or higherDistance from the day's average price 0.086 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9068 ≤ -0.9 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Upper wick · 15m feature.candle_upper_wick_15m 0.728 ≥ 0.72 Cascade clustering feature.cascade_clustering_index 0.5119 ≥ 0.51 OI velocity percentile feature.oi_velocity_pctrank 0.9316 ≥ 0.93 Realized vol percentile feature.realized_vol_pctrank 0.9974 ≥ 0.99 Return · 15m feature.ret_15m 0.02894 ≥ 0.028 Return · 1h feature.ret_1h 0.03878 ≥ 0.038 VWAP distance · day feature.vwap_dist 0.08637 ≥ 0.086
Two other reading times we tried 15 and 9 matches
1 minute before (16:59): order book tilt -0.9 or lower, open interest change rank 0.93 or higher, volatility rank 0.99 or higher.
Book imbalance · top levels ≤ -0.9 and OI velocity percentile ≥ 0.93 and Realized vol percentile ≥ 0.99
15 matches.
Of the 15 matches, 13 came before the rise began, 2 during it and 0 after it.
15 minutes before (16:45): sweep + reclaim (15m) is bearish, open interest change rank 0.97 or higher, volatility rank 0.99 or higher.
Sweep + reclaim · 15m bearish and OI velocity percentile ≥ 0.97 and Realized vol percentile ≥ 0.99
9 matches.
Of the 9 matches, 9 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 17:00 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
Same 3 conditions on HEI, 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.