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-MBTWUSDT rose 26% on 27 August 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 04:00 hour at 0.3863 and reached a highest trade of 0.4878 in the 23:00 hour; the tested readings were taken at 04:00.
What stood out at 04:00
- Order book lopsidedness0.07932Tested: 0.08 or lower
- 1-hour range against usual0.287Tested: 0.29 or lower
- 4-hour range against usual0.4294Tested: 0.43 or lower
04:00 always meets its own rules.
What the record says
30 minutes later, 3 of 10 were at or above the match price and 7 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 · 10 of 43,201 minutes · saved text
- Order book lopsidedness 0.08 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 ≤ 0.08 · feature.book_imbalance_pctrank
- 1-hour range against usual 0.29 or lower. The last finished 1-hour candle's high to low range, as a multiple of its usual range.feature.candle_compression_1h ≤ 0.29 · feature.candle_compression_1h
- 4-hour range against usual 0.43 or lower. The last finished 4-hour candle's high to low range, as a multiple of its usual range.feature.candle_compression_4h ≤ 0.43 · feature.candle_compression_4h
Read at 24 hours before the move.
Read at 04:00 UTC on 26 August, 24 hours before the selected 04:00 start.
BTW only, 3 August to 1 September 2026 (UTC, ending 2 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every BTW 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 04:00 start was picked automatically after the move.
BTWUSDT stored readings end 2026-09-02 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#ea3c43bd @ dataset 489ec93a, counted 3 Sep 2026 07:51 UTC.
Saved summary text, as written 3 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 10 times in the 43,201 minutes searched. What followed was more often lower: 7 of the 10 matches with a complete 30 minutes forward fell (70%).
About 0.3 a day over 31 days, but 2026-08-30 alone holds 40% of them: this is close to a single episode.
Picked after the rise, on one market.
When the matches happened
Of the 10 matches, 5 came before the rise began, 1 during it and 4 after it.
Neighbouring minutes overlap, so these are not 10 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 · 26 Aug 04:00 UTC · 5 of 41 stood out
Order book lopsidedness 0.08 or lower1-hour range against usual 0.29 or lower4-hour range against usual 0.43 or lowerContainment (15m) is insideLiquidation bunching 0.67 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.07932 ≤ 0.08 feature.candle_compression_1h feature.candle_compression_1h 0.287 ≤ 0.29 feature.candle_compression_4h feature.candle_compression_4h 0.4294 ≤ 0.43 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.6727 ≥ 0.67 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
No readings were recorded for this minute.
Hourly candles around the risefull context, lead-up, move
The 04:00 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 BTW, 4 July to 2 August 2026.
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.