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-MGRASSUSDT rose 87% on 25 September 2026
Picked after the rise, on one market.
Next stepWhat happened
Price opened the 04:00 hour at 0.4386 and reached a highest trade of 0.819 in the 20:00 hour; the tested readings were taken at 03:59.
What stood out at 03:59
- Order book lopsidedness0.08154Tested: 0.082 or lower
- Sweep + reclaim (1h)bearishTested: is bearish
- Liquidation bunching0.6496Tested: 0.64 or higher
03:59 always meets its own rules.
What the record says
Too few results to compare
Price at least 2% higher after 30 minutes
11 matches in 43,201 minutes checked.
Picked after the rise, on one market.
Evidence
Does it hold on other markets?
No result for these markets has been measured; nothing runs until you press Run.
Exactly what was counted3 conditions · 11 of 43,201 minutes · saved text
- Order book lopsidedness 0.082 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 ≤ 0.082 · feature.book_imbalance_pctrank
- Sweep + reclaim (1h) is bearish.Sweep + reclaim · 1h bearish · feature.candle_sweep_reclaim_1h
- Liquidation bunching 0.64 or higher. How bunched in time recent liquidations were; higher means more bunched, and it stays below 1.Cascade clustering ≥ 0.64 · feature.cascade_clustering_index
Read at 1 minute before the move.
Read at 03:59 UTC on 25 September, one minute before the selected 04:00 start.
GRASS only, 1 September to 30 September 2026 (UTC, ending 1 October 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every GRASS 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.
GRASSUSDT stored readings end 2026-10-01 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#10ab2cdc @ dataset c764b05a, counted 1 Oct 2026 09:40 UTC.
Saved summary text, as written 1 Oct 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 more often lower: 9 of the 11 matches with a complete 30 minutes forward fell (82%).
2 rose and 9 fell over 11 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
About 0.4 a day, on 5 of 31 days: spread through the record rather than one event.
It counts the single minute on 1 October as a day.
The other reading times, as written
From 15 minutes before
Minutes like this appeared only 11 times in the 43,201 minutes searched. What followed was more often lower: 9 of the 11 matches with a complete 30 minutes forward fell (82%).
2 rose and 9 fell over 11 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
About 0.4 a day, on 5 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 8 times in the 43,201 minutes searched. What followed was more often lower: 8 of the 8 matches with a complete 30 minutes forward fell (100%).
0 rose and 8 fell over 8 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
About 0.3 a day, on 5 of 31 days: spread through the record rather than one event.
Picked after the rise, on one market; the 11 matches came on 5 of 30 days, 8 during the rise.
When the matches happened5 of 30 days
- 24 Sep2 matches
- 25 Sep4 matches
- 26 Sep1 match
- 27 Sep2 matches
- 29 Sep2 matches
No matches on the other 25 days.
Of the 11 matches, 3 came before the rise began, 8 during it and 0 after it.
Neighbouring minutes overlap, so these are not 11 separate trials.
Picked after the rise, on one market; the 11 matches came on 5 of 30 days, 8 during the rise.
Other time frames30 minutes to 7 days
The answer uses 30 minutes, the time frame this study counted by default. Each row counts the same matches at a later close, in both directions. The bars show how often price was 2% or more higher at each time frame: first the matches, then any GRASS minute.
- 30 minutes
1 of 11 was 2% or more lower; any GRASS minute 1,551 of 42,748 (3.6%).
Every match has a 30-minute close.
At least 8 of these windows overlap the rise.
- 1 hour
1 of 11 was 2% or more lower; any GRASS minute 2,620 of 42,715 (6.1%).
Every match has a 1-hour close.
At least 8 of these windows overlap the rise.
- 4 hours
2 of 11 were 2% or more lower; any GRASS minute 6,449 of 42,539 (15.2%).
Every match has a 4-hour close.
At least 8 of these windows overlap the rise.
- 24 hours
1 of 11 was 2% or more lower; any GRASS minute 10,124 of 41,342 (24.5%).
Every match has a 24-hour close.
At least 8 of these windows overlap the rise.
- 72 hours
0 of 9 were 2% or more lower; any GRASS minute 8,596 of 38,481 (22.3%).
2 without a 72-hour close yet, left out.
At least 2 of these windows overlap the rise.
- 7 days
None of the 11 matches has a 7-day close yet, so there is no rate.
Any GRASS minute: 18,601 of 32,795 (56.7%) were 2% or more higher, 10,083 of 32,795 (30.7%) lower.
Picked after the rise, on one market; the 11 matches came on 5 of 30 days, 8 during the rise.
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 · 24 Sep 04:00 UTC · 8 of 88 stood out
Order book tilt 0.56 or higherOrder book lopsidedness 0.038 or lower1-hour range against usual 0.44 or lowerLiquidation bunching 0.64 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.562 ≥ 0.56 Book imbalance percentile feature.book_imbalance_pctrank 0.03732 ≤ 0.038 Compression · 1h feature.candle_compression_1h 0.4396 ≤ 0.44 Cascade clustering feature.cascade_clustering_index 0.6496 ≥ 0.64 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 65 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 65 12 to 720 4 hours before · 25 Sep 00:00 UTC · 7 of 88 stood out
15-minute range against usual 0.48 or lowerLiquidation bunching 0.64 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursMinutes to funding 1 or lowerShow the full readings
Reading Value at that minute Stored rule Compression · 15m feature.candle_compression_15m 0.4737 ≤ 0.48 Cascade clustering feature.cascade_clustering_index 0.6496 ≥ 0.64 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 85 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 85 12 to 720 Minutes to funding feature.mins_to_funding 0 ≤ 1 1 hour before · 25 Sep 03:00 UTC · 7 of 88 stood out
Sweep + reclaim (1h) is bearishLiquidation bunching 0.64 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours15-minute price change -0.014 or lowerShow the full readings
Reading Value at that minute Stored rule Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.6496 ≥ 0.64 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 88 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 88 12 to 720 Return · 15m feature.ret_15m -0.01439 ≤ -0.014 15 minutes before · 25 Sep 03:45 UTC · 8 of 88 stood out
Order book tilt -0.78 or lowerSweep + reclaim (1h) is bearishLiquidation bunching 0.64 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change -0.02 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.7845 ≤ -0.78 Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.6496 ≥ 0.64 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 88.75 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 88.75 12 to 720 Return · 1h feature.ret_1h -0.02015 ≤ -0.02 1 minute before · 25 Sep 03:59 UTC · 8 of 88 stood out
Order book lopsidedness 0.082 or lowerSweep + reclaim (1h) is bearishLiquidation bunching 0.64 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours15-minute price change -0.012 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.08154 ≤ 0.082 Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.6496 ≥ 0.64 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 88.98 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 3 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 88.98 12 to 720 Return · 15m feature.ret_15m -0.01216 ≤ -0.012
Two other reading times we tried 11 and 8 matches
15 minutes before (03:45): order book tilt -0.78 or lower, sweep + reclaim (1h) is bearish, liquidation bunching 0.64 or higher.
Book imbalance · top levels ≤ -0.78 and Sweep + reclaim · 1h bearish and Cascade clustering ≥ 0.64
11 matches: price was 2% or more higher after 30 minutes in 1 of 11, and 2% or more lower in 2 of 11.
Of the 11 matches, 3 came before the rise began, 8 during it and 0 after it.
1 hour before (03:00): sweep + reclaim (1h) is bearish, liquidation bunching 0.64 or higher, how many times the broken descending resistance had been tested 3 or higher.
Sweep + reclaim · 1h bearish and Cascade clustering ≥ 0.64 and how many times the broken descending resistance had been tested ≥ 3
8 matches: price was 2% or more higher after 30 minutes in 0 of 8, and 2% or more lower in 1 of 8.
Of the 8 matches, 2 came before the rise began, 6 during it and 0 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; the 11 matches came on 5 of 30 days, 8 during the rise.
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
- This market only
- The 608 eligible crypto markets · No result for these markets has been measured.
- Every recorded market
- 57 AI sector markets
- 518 sector crypto markets
Each opens Review the test.
Running needs a free account and uses your allowance; you see the cost first.
Starting defaults and coverage
Starting defaults: 2026-09-01 to 2026-10-01 UTC; finishes up 2% or more after 1 hour. Review or change the markets, dates, conditions and outcome before running. Current recorded classification and sector tags, not point-in-time membership. Historical membership may differ. Instrument history does not guarantee every setup input or outcome is present; actual study exclusions remain authoritative.