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-MAKEUSDT rose 92% on 27 July 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 06:00 hour at 0.0036 and reached a highest trade of 0.0069 in the 06:00 hour; the tested readings were taken at 05:45.
What stood out at 05:45
- Liquidation bunching0.5705Tested: 0.57 or higher
- 15-minute price change0.0252Tested: 0.025 or higher
- Distance from the day's average price0.03025Tested: 0.03 or higher
05:45 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 · 145 of 43,201 minutes · saved text
Saved summary text, as written 3 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 145 times in the 43,201 minutes searched (0.3%). What followed was close to a coin flip: 68 rose and 77 fell over the next 30 minutes (145 of the 145 matches have a complete 30 minutes forward).
About 4.7 a day, on 22 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 179 times in the 43,201 minutes searched (0.4%). What followed was close to a coin flip: 91 rose and 88 fell over the next 30 minutes (179 of the 179 matches have a complete 30 minutes forward).
About 5.8 a day, on 23 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 1 time in the 43,201 minutes searched. What followed leaned down: 1 of the 1 matches with a complete 30 minutes forward fell (100%).
About 0 a day over 31 days, but 2026-07-27 alone holds 100% of them: this is close to a single episode.
Picked after the rise, on one market.
- Liquidation bunching 0.57 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.57 · feature.cascade_clustering_index
- 15-minute price change 0.025 or higher. Close to close change over the last 15 minutes, as a fraction of price.Return · 15m ≥ 0.025 · feature.ret_15m
- Distance from the day's average price 0.03 or higher. How far price sat above or below the day's volume weighted average, as a fraction of it.VWAP distance · day ≥ 0.03 · feature.vwap_dist
Read at 15 minutes before the move.
Read at 05:45 UTC on 27 July, 15 minutes before the selected 06:00 start.
AKE only, 4 July to 2 August 2026 (UTC, ending 3 August 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every AKE 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 06:00 start was picked automatically after the move.
AKEUSDT stored readings end 2026-08-03 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#b50e99e4 @ dataset b91f2197, counted 3 Aug 2026 06:59 UTC.
When the matches happened
Of the 145 matches, 112 came before the rise began, 0 during it and 33 after it.
Neighbouring minutes overlap, so these are not 145 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 · 26 Jul 06:00 UTC · 6 of 33 stood out
Order book tilt 0.84 or higherOrder book lopsidedness 0.072 or lowerSweep + reclaim (15m) is bullishLiquidation bunching 0.64 or higher1-hour price change -0.02 or lowerDistance from the day's average price -0.029 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8437 ≥ 0.84 Book imbalance percentile feature.book_imbalance_pctrank 0.07147 ≤ 0.072 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Cascade clustering feature.cascade_clustering_index 0.6431 ≥ 0.64 Return · 1h feature.ret_1h -0.02014 ≤ -0.02 VWAP distance · day feature.vwap_dist -0.02972 ≤ -0.029 4 hours before · 27 Jul 02:00 UTC · 6 of 33 stood out
Order book tilt -0.56 or lowerLiquidation bunching 0.57 or higherOpen interest change rank 0.92 or higher15-minute price change 0.02 or higher1-hour price change 0.044 or higherDistance from the day's average price 0.032 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5672 ≤ -0.56 Cascade clustering feature.cascade_clustering_index 0.5704 ≥ 0.57 OI velocity percentile feature.oi_velocity_pctrank 0.9271 ≥ 0.92 Return · 15m feature.ret_15m 0.02055 ≥ 0.02 Return · 1h feature.ret_1h 0.04405 ≥ 0.044 VWAP distance · day feature.vwap_dist 0.03216 ≥ 0.032 1 hour before · 27 Jul 05:00 UTC · 8 of 33 stood out
Order book tilt 0.92 or higherOrder book lopsidedness 0.025 or lowerContainment (15m) is insideLiquidation bunching 0.57 or higherVolatility rank 0.99 or higher15-minute price change 0.01 or higher1-hour price change 0.052 or higherDistance from the day's average price 0.043 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9282 ≥ 0.92 Book imbalance percentile feature.book_imbalance_pctrank 0.0249 ≤ 0.025 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5707 ≥ 0.57 Realized vol percentile feature.realized_vol_pctrank 0.9999 ≥ 0.99 Return · 15m feature.ret_15m 0.01049 ≥ 0.01 Return · 1h feature.ret_1h 0.05233 ≥ 0.052 VWAP distance · day feature.vwap_dist 0.04324 ≥ 0.043 15 minutes before · 27 Jul 05:45 UTC · 3 of 33 stood out
Liquidation bunching 0.57 or higher15-minute price change 0.025 or higherDistance from the day's average price 0.03 or higherShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.5705 ≥ 0.57 Return · 15m feature.ret_15m 0.0252 ≥ 0.025 VWAP distance · day feature.vwap_dist 0.03025 ≥ 0.03 1 minute before · 27 Jul 05:59 UTC · 4 of 33 stood out
Order book tilt -0.9 or lowerLiquidation bunching 0.57 or higher15-minute price change 0.02 or higherDistance from the day's average price 0.054 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9043 ≤ -0.9 Cascade clustering feature.cascade_clustering_index 0.5702 ≥ 0.57 Return · 15m feature.ret_15m 0.02089 ≥ 0.02 VWAP distance · day feature.vwap_dist 0.05439 ≥ 0.054
Two other reading times we tried 179 and 1 matches
1 minute before (05:59): order book tilt -0.9 or lower, liquidation bunching 0.57 or higher, 15-minute price change 0.02 or higher.
Book imbalance · top levels ≤ -0.9 and Cascade clustering ≥ 0.57 and Return · 15m ≥ 0.02
179 matches.
Of the 179 matches, 128 came before the rise began, 0 during it and 51 after it.
1 hour before (05:00): order book tilt 0.92 or higher, order book lopsidedness 0.025 or lower, volatility rank 0.99 or higher.
Book imbalance · top levels ≥ 0.92 and Book imbalance percentile ≤ 0.025 and Realized vol percentile ≥ 0.99
1 match.
Of the 1 match, 1 came before the rise began, 0 during it and 0 after it.
Fewer than 30 results, so no rate is printed.
The saved study leads with 05:45: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market.
Hourly candles around the risefull context, lead-up, move
The 06:00 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 AKE, 4 June to 3 July 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.