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-MPROMUSDT rose 87% on 27 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 03:00 hour at 4.219 and reached a highest trade of 7.888 in the 02:00 hour; the tested readings were taken at 23:00.
What stood out at 23:00
- Order book tilt0.5635Tested: 0.56 or higher
- Order book lopsidedness0.0574Tested: 0.058 or lower
- Containment (15m)insideTested: is inside
23:00 always meets its own rules.
What the record says
30 minutes later, 24 of 48 were at or above the match price and 24 below; no reference was saved
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 · 48 of 43,201 minutes · saved text
- Order book tilt 0.56 or higher. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≥ 0.56 · feature.book_imbalance
- Order book lopsidedness 0.058 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 ≤ 0.058 · feature.book_imbalance_pctrank
- Containment (15m) is inside.Containment · 15m inside · feature.candle_containment_15m
Read at 4 hours before the move.
Read at 23:00 UTC on 26 August, four hours before the selected 03:00 start.
PROM only, 4 August to 2 September 2026 (UTC, ending 3 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every PROM 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.
PROMUSDT stored readings end 2026-09-03 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#40f7fd7d @ dataset e92709f8, counted 4 Sep 2026 07:57 UTC.
Saved summary text, as written 4 Sep 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 48 times in the 43,201 minutes searched (0.1%). What followed was close to a coin flip: 24 rose and 24 fell over the next 30 minutes (48 of the 48 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 7 of 48 complete windows (14.6%), against 6.9% with no condition (2,995 of 43,159): 2.10x.
This reports the time frame with the biggest gap from any minute, chosen after counting. Longer windows can run through the rise.
Best point inside 30 minutes reached +5% or more in 4 of 48 complete windows; worst point fell 5% or more in 3 of 48.
About 1.5 a day, on 19 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market.
When the matches happened
Of the 48 matches, 21 came before the rise began, 14 during it and 13 after it.
Neighbouring minutes overlap, so these are not 48 separate trials.
Picked after the rise, on one market.
Other time frames
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 30 minutes.
After 30 minutes this setup fell 2% or more in 7 of 48 complete windows (14.6%), against 6.9% with no condition (2,995 of 43,159): 2.10x.
Along the way (the highest and lowest price inside 30 minutes, not the close):
Best point inside 30 minutes reached +5% or more in 4 of 48 complete windows; worst point fell 5% or more in 3 of 48.
Picked after the rise, on one market.
Readings at five times before the rise24 hours to 1 minute before
Highlights follow fixed rules, not significance tests. Proposed conditions round values or use ranges; inspect them before running.
24 hours before
No readings were recorded for this minute.
4 hours before · 26 Aug 23:00 UTC · 5 of 53 stood out
Order book tilt 0.56 or higherOrder book lopsidedness 0.058 or lowerContainment (15m) is insideSweep + reclaim (1h) is bearishDistance from the day's average price 0.025 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.5635 ≥ 0.56 Book imbalance percentile feature.book_imbalance_pctrank 0.0574 ≤ 0.058 Containment · 15m feature.candle_containment_15m inside inside Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish VWAP distance · day feature.vwap_dist 0.02513 ≥ 0.025 1 hour before
No readings were recorded for this minute.
15 minutes before
No readings were recorded for this minute.
1 minute before
No readings were recorded for this minute.
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 PROM, 5 July to 3 August 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.