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-MCYSUSDT fell 29% on 28 July 2026
Picked after the fall, on one market.
Next stepWhat happened
Price opened the 15:00 hour at 0.3065 and reached a lowest trade of 0.2191 in the 08:00 hour; the tested readings were taken at 14:00.
What stood out at 14:00
- Order book tilt0.6571Tested: 0.65 or higher
- Liquidation bunching0.6089Tested: 0.6 or higher
- Taker buy share (15m)0.6553Tested: 0.65 or higher
14:00 always meets its own rules.
What the record says
No counts were saved to compare, only the summary text
Picked after the fall, on one market.
Evidence
Does it hold on other dates?
Nothing runs until you press Run.
Exactly what was counted3 conditions · 355 of 43,201 minutes · saved text
Saved summary text, as written 5 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 are common here: 355 of the 43,201 minutes searched (0.8%), about 11 a day. What followed was close to a coin flip: 164 rose and 166 fell over the next 30 minutes (330 of the 355 matches have a complete 30 minutes forward).
About 11 a day, on 30 of 31 days: spread through the record rather than one event.
The other reading times, as written
From 4 hours before
Minutes like this appeared only 8 times in the 43,201 minutes searched. What followed leaned up: 5 of the 8 matches with a complete 30 minutes forward rose (63%).
About 0.3 a day, on 8 of 31 days: spread through the record rather than one event.
Picked after the fall, on one market.
- Order book tilt 0.65 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.65 · feature.book_imbalance
- Liquidation bunching 0.6 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.6 · feature.cascade_clustering_index
- Taker buy share (15m) 0.65 or higher.Taker buy share · 15m ≥ 0.65 · feature.taker_buy_ratio_15m
Read at 1 hour before the move.
Read at 14:00 UTC on 28 July, one hour before the selected 15:00 start.
CYS only, 5 July to 3 August 2026 (UTC, ending 4 August 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every CYS 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 15:00 start was picked automatically after the move.
CYSUSDT stored readings end 2026-08-04 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#ccd7bf88 @ dataset 461da594, counted 5 Aug 2026 02:50 UTC.
When the matches happened
Of the 355 matches, 287 came before the fall began, 6 during it and 62 after it.
Neighbouring minutes overlap, so these are not 355 separate trials.
Picked after the fall, on one market.
Readings at five times before the fall24 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 · 27 Jul 15:00 UTC · 4 of 39 stood out
Order book tilt -0.66 or lowerContainment (15m) is insideLower wick (15m) 0.66 or higherLiquidation bunching 0.6 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.6615 ≤ -0.66 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 0.608 ≥ 0.6 4 hours before · 28 Jul 11:00 UTC · 5 of 39 stood out
Order book tilt 0.82 or higher15-minute range against usual 0.43 or lowerUpper wick (15m) 0.72 or higherLiquidation bunching 0.6 or higherVolatility rank 0.9 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.8229 ≥ 0.82 Compression · 15m feature.candle_compression_15m 0.4244 ≤ 0.43 Upper wick · 15m feature.candle_upper_wick_15m 0.7273 ≥ 0.72 Cascade clustering feature.cascade_clustering_index 0.6089 ≥ 0.6 Realized vol percentile feature.realized_vol_pctrank 0.909 ≥ 0.9 1 hour before · 28 Jul 14:00 UTC · 3 of 39 stood out
Order book tilt 0.65 or higherLiquidation bunching 0.6 or higherTaker buy share (15m) 0.65 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.6571 ≥ 0.65 Cascade clustering feature.cascade_clustering_index 0.6089 ≥ 0.6 Taker buy share · 15m feature.taker_buy_ratio_15m 0.6553 ≥ 0.65 15 minutes before · 28 Jul 14:45 UTC · 1 of 39 stood out
Liquidation bunching 0.6 or higherShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.6089 ≥ 0.6 1 minute before · 28 Jul 14:59 UTC · 1 of 39 stood out
Liquidation bunching 0.6 or higherShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.6089 ≥ 0.6
Two other reading times we tried 0 and 8 matches
1 minute before (14:59): liquidation bunching 0.6 or higher.
Cascade clustering ≥ 0.6
No matches.
4 hours before (11:00): order book tilt 0.82 or higher, 15-minute range against usual 0.43 or lower, volatility rank 0.9 or higher.
Book imbalance · top levels ≥ 0.82 and Compression · 15m ≤ 0.43 and Realized vol percentile ≥ 0.9
8 matches.
Of the 8 matches, 7 came before the fall began, 0 during it and 1 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 14:00 because it is the only set with at least 30 matches before the fall.
Picked after the fall, on one market.
Hourly candles around the fallfull context, lead-up, move
The 15:00 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 CYS, 5 June to 4 July 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.