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-MBTRUSDT rose 394% on 26 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 03:00 hour at 0.03639 and reached a highest trade of 0.1796 in the 04:00 hour; the tested readings were taken at 02:59.
What stood out at 02:59
- Order book tilt-0.5108Tested: -0.51 or lower
- Order book lopsidedness0.0621Tested: 0.063 or lower
- Volatility rank0.9946Tested: 0.99 or higher
02:59 always meets its own rules.
What the record says
30 minutes later, 6 of 11 were at or above the match price and 5 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 · 11 of 43,201 minutes · saved text
- Order book tilt -0.51 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.51 · feature.book_imbalance
- Order book lopsidedness 0.063 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 ≤ 0.063 · feature.book_imbalance_pctrank
- Volatility rank 0.99 or higher. How volatile the last hour was against this market's history, on a 0 to 1 scale.Realized vol percentile ≥ 0.99 · feature.realized_vol_pctrank
Read at 1 minute before the move.
Read at 02:59 UTC on 26 August, one minute before the selected 03:00 start.
BTR only, 2 August to 31 August 2026 (UTC, ending 1 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every BTR 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.
BTRUSDT stored readings end 2026-09-01 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#d5cef6f6 @ dataset 9bf4ae59, counted 1 Sep 2026 07:46 UTC.
Saved summary text, as written 1 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 only 11 times in the 43,201 minutes searched. What followed was close to a coin flip: 6 rose and 5 fell over the next 30 minutes (11 of the 11 matches have a complete 30 minutes forward).
About 0.4 a day, on 10 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market.
When the matches happened
Of the 11 matches, 9 came before the rise began, 0 during it and 2 after it.
Neighbouring minutes overlap, so these are not 11 separate trials.
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
No readings were recorded for this minute.
1 hour before
No readings were recorded for this minute.
15 minutes before
No readings were recorded for this minute.
1 minute before · 26 Aug 02:59 UTC · 8 of 39 stood out
Order book tilt -0.51 or lowerOrder book lopsidedness 0.063 or lower15-minute range against usual 7.4 or higherLiquidation bunching 0.62 or higherVolatility rank 0.99 or higher15-minute price change 0.017 or higher1-hour price change 0.092 or higherDistance from the day's average price 0.036 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5108 ≤ -0.51 Book imbalance percentile feature.book_imbalance_pctrank 0.0621 ≤ 0.063 Compression · 15m feature.candle_compression_15m 7.451 ≥ 7.4 Cascade clustering feature.cascade_clustering_index 0.6223 ≥ 0.62 Realized vol percentile feature.realized_vol_pctrank 0.9946 ≥ 0.99 Return · 15m feature.ret_15m 0.01758 ≥ 0.017 Return · 1h feature.ret_1h 0.09227 ≥ 0.092 VWAP distance · day feature.vwap_dist 0.03643 ≥ 0.036
Hourly candles around the risefull context, lead-up, move
The 03:00 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 BTR, 3 July to 1 August 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.