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-MSKYAIUSDT rose 129% on 6 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 03:00 hour at 0.06245 and reached a highest trade of 0.1431 in the 07:00 hour; the tested readings were taken at 02:00.
What stood out at 02:00
- Order book tilt-0.8815Tested: -0.88 or lower
- Liquidation bunching0.5635Tested: 0.56 or higher
- 15-minute price change0.03091Tested: 0.03 or higher
02:00 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 · 40 of 43,201 minutes · saved text
Saved summary text, as written 14 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 40 times in the 43,201 minutes searched (<0.1%). What followed was close to a coin flip: 20 rose and 20 fell over the next 30 minutes (40 of the 40 matches have a complete 30 minutes forward).
About 1.3 a day, on 10 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 13 times in the 43,201 minutes searched. What followed was close to a coin flip: 6 rose and 7 fell over the next 30 minutes (13 of the 13 matches have a complete 30 minutes forward).
About 0.4 a day, on 7 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this appeared only 24 times in the 43,201 minutes searched. What followed was close to a coin flip: 11 rose and 13 fell over the next 30 minutes (24 of the 24 matches have a complete 30 minutes forward).
About 0.8 a day, on 11 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market.
- Order book tilt -0.88 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.88 · feature.book_imbalance
- Liquidation bunching 0.56 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.56 · feature.cascade_clustering_index
- 15-minute price change 0.03 or higher. Close to close change over the last 15 minutes, as a fraction of price.Return · 15m ≥ 0.03 · feature.ret_15m
Read at 1 hour before the move.
Read at 02:00 UTC on 6 August, one hour before the selected 03:00 start.
SKYAI only, 14 July to 12 August 2026 (UTC, ending 13 August 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every SKYAI 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 03:00 start was picked automatically after the move.
SKYAIUSDT stored readings end 2026-08-13 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#2424102e @ dataset 1a5d8642, counted 14 Aug 2026 02:54 UTC.
When the matches happened
Of the 40 matches, 17 came before the rise began, 9 during it and 14 after it.
Neighbouring minutes overlap, so these are not 40 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 · 5 Aug 03:00 UTC · 5 of 39 stood out
Order book tilt 0.86 or higherSweep + reclaim (15m) is bearishLiquidation bunching 0.62 or higher1-hour price change 0.029 or higherDistance from the day's average price 0.083 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8677 ≥ 0.86 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.6255 ≥ 0.62 Return · 1h feature.ret_1h 0.02962 ≥ 0.029 VWAP distance · day feature.vwap_dist 0.08333 ≥ 0.083 4 hours before · 5 Aug 23:00 UTC · 4 of 39 stood out
Liquidation bunching 0.58 or higherVolatility rank 0.091 or lower15-minute price change -0.013 or lowerDistance from the day's average price 0.1 or higherShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.5813 ≥ 0.58 Realized vol percentile feature.realized_vol_pctrank 0.09084 ≤ 0.091 Return · 15m feature.ret_15m -0.01374 ≤ -0.013 VWAP distance · day feature.vwap_dist 0.1049 ≥ 0.1 1 hour before · 6 Aug 02:00 UTC · 4 of 39 stood out
Order book tilt -0.88 or lowerLiquidation bunching 0.56 or higher15-minute price change 0.03 or higher1-hour price change 0.059 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.8815 ≤ -0.88 Cascade clustering feature.cascade_clustering_index 0.5635 ≥ 0.56 Return · 15m feature.ret_15m 0.03091 ≥ 0.03 Return · 1h feature.ret_1h 0.05993 ≥ 0.059 15 minutes before · 6 Aug 02:45 UTC · 6 of 39 stood out
Order book tilt 0.96 or higherOrder book lopsidedness 0.91 or higherLiquidation bunching 0.57 or higher15-minute price change -0.012 or lower1-hour price change -0.059 or lowerDistance from the day's average price -0.063 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9636 ≥ 0.96 Book imbalance percentile feature.book_imbalance_pctrank 0.9135 ≥ 0.91 Cascade clustering feature.cascade_clustering_index 0.5766 ≥ 0.57 Return · 15m feature.ret_15m -0.01269 ≤ -0.012 Return · 1h feature.ret_1h -0.05998 ≤ -0.059 VWAP distance · day feature.vwap_dist -0.06336 ≤ -0.063 1 minute before · 6 Aug 02:59 UTC · 3 of 39 stood out
Liquidation bunching 0.57 or higher1-hour price change -0.074 or lowerDistance from the day's average price -0.044 or lowerShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.5766 ≥ 0.57 Return · 1h feature.ret_1h -0.0744 ≤ -0.074 VWAP distance · day feature.vwap_dist -0.04476 ≤ -0.044
Two other reading times we tried 13 and 24 matches
1 minute before (02:59): liquidation bunching 0.57 or higher, 1-hour price change -0.074 or lower, distance from the day's average price -0.044 or lower.
Cascade clustering ≥ 0.57 and Return · 1h ≤ -0.074 and VWAP distance · day ≤ -0.044
13 matches.
Of the 13 matches, 6 came before the rise began, 2 during it and 5 after it.
15 minutes before (02:45): order book tilt 0.96 or higher, order book lopsidedness 0.91 or higher, liquidation bunching 0.57 or higher.
Book imbalance · top levels ≥ 0.96 and Book imbalance percentile ≥ 0.91 and Cascade clustering ≥ 0.57
24 matches.
Of the 24 matches, 16 came before the rise began, 3 during it and 5 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 03:00 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 SKYAI, 14 June to 13 July 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.