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-MSYNUSDT rose 157% on 15 September 2026
Picked after the rise, on one market.
What happened
Price opened the 22:00 hour at 0.0848 and reached a highest trade of 0.2179 in the 07:00 hour; the tested readings were taken at 21:59.
What stood out at 21:59
- Order book tilt-0.7312Tested: -0.73 or lower
- Book capturenativeTested: is native
- Open interest change rank0.9995Tested: 0.99 or higher
21:59 always meets its own rules.
What the record says
More often than any SYN minute, in this sample
Price at least 2% higher after 30 minutes
95 matches in 43,201 minutes checked.
Picked after the rise, on one market.
Evidence
No test to open
Multiple recorded sectors: sector_crypto, sector_defi. Choose one explicitly.
Exactly what was counted3 conditions · 95 of 43,201 minutes · saved text
- Order book tilt -0.73 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.73 · feature.book_imbalance
- Book capture is native.Book capture native · feature.book_source
- Open interest change rank 0.99 or higher. How unusual the change in open positions was, opening or closing, on a 0 to 1 scale.OI change magnitude score ≥ 0.99 · feature.oi_velocity_pctrank
Read at 1 minute before the move.
Read at 21:59 UTC on 15 September, one minute before the selected 22:00 start.
SYN only, 23 August to 21 September 2026 (UTC, ending 22 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every SYN 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 22:00 start was picked automatically after the move.
SYNUSDT stored readings end 2026-09-22 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#c4ec9a97 @ dataset 85fdc316, counted 22 Sep 2026 08:33 UTC.
Saved summary text, as written 22 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 95 times in the 43,201 minutes searched (0.2%). What followed was close to a coin flip: 43 rose and 52 fell over the next 30 minutes (95 of the 95 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 12 of 95 complete windows (12.6%), against 4.5% with no condition (1,919 of 43,075): 2.84x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 3 of its 95 windows overlap the rise.
Best point inside 30 minutes reached +5% or more in 12 of 95 complete windows; worst point fell 5% or more in 8 of 95.
About 3.1 a day, on 29 of 31 days: spread through the record rather than one event.
It counts the single minute on 22 September as a day.
The other reading times, as written
From 15 minutes before
Minutes like this appeared 97 times in the 43,201 minutes searched (0.2%). What followed was close to a coin flip: 50 rose and 47 fell over the next 30 minutes (97 of the 97 matches have a complete 30 minutes forward).
After 30 minutes this setup rose 2% or more in 16 of 97 complete windows (16.5%), against 5.3% with no condition (2,278 of 43,075): 3.12x.
About 3.1 a day, on 30 of 31 days: spread through the record rather than one event.
From 1 hour before
Minutes like this appeared only 19 times in the 43,201 minutes searched. What followed was more often higher: 11 of the 19 matches with a complete 30 minutes forward rose (58%).
11 rose and 8 fell over 19 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 0.6 a day over 31 days, but 2026-09-16 alone holds 42% of them: this is close to a single episode.
Picked after the rise, on one market; the 95 matches came on 29 of 30 days, 3 during the rise.
When the matches happened29 of 30 days
- 23 Aug4 matches
- 24 Aug3 matches
- 25 Aug1 match
- 26 Aug1 match
- 27 Aug2 matches
- 29 Aug4 matches
- 30 Aug3 matches
- 31 Aug2 matches
- 1 Sep4 matches
- 2 Sep6 matches
- 3 Sep3 matches
- 4 Sep2 matches
- 5 Sep3 matches
- 6 Sep1 match
- 7 Sep2 matches
- 8 Sep2 matches
- 9 Sep3 matches
- 10 Sep1 match
- 11 Sep4 matches
- 12 Sep2 matches
- 13 Sep6 matches
- 14 Sep3 matches
- 15 Sep3 matches
- 16 Sep6 matches
- 17 Sep5 matches
- 18 Sep4 matches
- 19 Sep6 matches
- 20 Sep1 match
- 21 Sep8 matches
No matches on the other 1 day.
Of the 95 matches, 64 came before the rise began, 3 during it and 28 after it.
Neighbouring minutes overlap, so these are not 95 separate trials.
Picked after the rise, on one market; the 95 matches came on 29 of 30 days, 3 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 SYN minute.
- 30 minutes
12 of 95 (12.6%) were 2% or more lower; any SYN minute 1,919 of 43,075 (4.5%).
Every match has a 30-minute close.
At least 3 of these windows overlap the rise.
- 1 hour
13 of 95 (13.7%) were 2% or more lower; any SYN minute 3,060 of 43,047 (7.1%).
Every match has a 1-hour close.
At least 3 of these windows overlap the rise.
- 4 hours
19 of 94 (20.2%) were 2% or more lower; any SYN minute 5,433 of 42,865 (12.7%).
1 without a 4-hour close yet, left out.
At least 3 of these windows overlap the rise.
- 24 hours
28 of 87 (32.2%) were 2% or more lower; any SYN minute 14,835 of 41,666 (35.6%).
8 without a 24-hour close yet, left out.
At least 3 of these windows overlap the rise.
- 72 hours
27 of 80 (33.8%) were 2% or more lower; any SYN minute 18,347 of 38,789 (47.3%).
15 without a 72-hour close yet, left out.
At least 12 of these windows overlap the rise.
- 7 days
34 of 62 (54.8%) were 2% or more lower; any SYN minute 21,707 of 33,045 (65.7%).
33 without a 7-day close yet, left out.
At least 19 of these windows overlap the rise.
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 12 of 95 complete windows (12.6%), against 4.5% with no condition (1,919 of 43,075): 2.84x.
At least 3 of those windows ran through the rise itself, so it partly counts the rise as an outcome.
Along the way (the highest and lowest price inside 30 minutes, not the close):
Best point inside 30 minutes reached +5% or more in 12 of 95 complete windows; worst point fell 5% or more in 8 of 95.
Picked after the rise, on one market; the 95 matches came on 29 of 30 days, 3 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 · 14 Sep 22:00 UTC · 15 of 87 stood out
Order book tilt -0.92 or lowerOrder book lopsidedness 0.93 or higherBook capture is native15-minute range against usual 0.43 or lower1-hour range against usual 4.7 or higher4-hour range against usual 2.5 or higherLower wick (15m) 0.63 or higherLiquidation bunching 0.5 or higherDepth capture is liveHow many times the broken descending resistance had been tested 3 or higherTouches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hours1-hour price change -0.075 or lowerTaker buy share (15m) 0.68 or higherDistance from the day's average price -0.024 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9232 ≤ -0.92 Book imbalance percentile feature.book_imbalance_pctrank 0.9387 ≥ 0.93 Book capture feature.book_source native native Compression · 15m feature.candle_compression_15m 0.4258 ≤ 0.43 Compression · 1h feature.candle_compression_1h 4.731 ≥ 4.7 Compression · 4h feature.candle_compression_4h 2.507 ≥ 2.5 Lower wick · 15m feature.candle_lower_wick_15m 0.6364 ≥ 0.63 Cascade clustering feature.cascade_clustering_index 0.5057 ≥ 0.5 Depth capture feature.depth_source live live how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 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 631 12 to 720 Return · 1h feature.ret_1h -0.07539 ≤ -0.075 Taker buy share · 15m feature.taker_buy_ratio_15m 0.6802 ≥ 0.68 VWAP distance · day feature.vwap_dist -0.02415 ≤ -0.024 4 hours before · 15 Sep 18:00 UTC · 14 of 87 stood out
Order book lopsidedness 0.096 or lowerBook capture is native1-hour range against usual 3.9 or higherSweep + reclaim (1h) is bearishLiquidation bunching 0.51 or higherDepth capture is liveThe distance from price back to the broken descending resistance between -0.5 and 0.5How 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 hoursVolatility rank 0.99 or higher15-minute price change -0.029 or lower1-hour price change -0.026 or lowerShow the full readings
Reading Value at that minute Stored rule Book imbalance percentile feature.book_imbalance_pctrank 0.09585 ≤ 0.096 Book capture feature.book_source native native Compression · 1h feature.candle_compression_1h 3.909 ≥ 3.9 Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.511 ≥ 0.51 Depth capture feature.depth_source live live the distance from price back to the broken descending resistance feature.desc_resistance_broken_dist_atr -0.443 -0.5 to 0.5 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 22 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 651 12 to 720 Realized vol percentile feature.realized_vol_pctrank 0.9957 ≥ 0.99 Return · 15m feature.ret_15m -0.0298 ≤ -0.029 Return · 1h feature.ret_1h -0.02632 ≤ -0.026 1 hour before · 15 Sep 21:00 UTC · 10 of 87 stood out
Book capture is native4-hour range against usual 2.7 or higherContainment (15m) is insideLiquidation bunching 0.51 or higherDepth capture is liveThe distance from price back to the broken descending resistance between -0.5 and 0.5How 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 capture feature.book_source native native Compression · 4h feature.candle_compression_4h 2.756 ≥ 2.7 Containment · 15m feature.candle_containment_15m inside inside Cascade clustering feature.cascade_clustering_index 0.5145 ≥ 0.51 Depth capture feature.depth_source live live the distance from price back to the broken descending resistance feature.desc_resistance_broken_dist_atr -0.4109 -0.5 to 0.5 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 25 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 654 12 to 720 15 minutes before · 15 Sep 21:45 UTC · 12 of 87 stood out
Order book tilt 0.67 or higherBook capture is native4-hour range against usual 2.7 or higherLiquidation bunching 0.51 or higherDepth capture is liveHow 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 hoursOpen interest change rank 0.99 or higher15-minute price change 0.017 or higher1-hour price change 0.023 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.6704 ≥ 0.67 Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 2.756 ≥ 2.7 Cascade clustering feature.cascade_clustering_index 0.5145 ≥ 0.51 Depth capture feature.depth_source live live 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 25.75 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 654.8 12 to 720 OI change magnitude score feature.oi_velocity_pctrank 0.9928 ≥ 0.99 Return · 15m feature.ret_15m 0.01711 ≥ 0.017 Return · 1h feature.ret_1h 0.02337 ≥ 0.023 1 minute before · 15 Sep 21:59 UTC · 13 of 87 stood out
Order book tilt -0.73 or lowerBook capture is native4-hour range against usual 2.7 or higherLiquidation bunching 0.51 or higherDepth capture is liveHow 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 hoursOpen interest change rank 0.99 or higher15-minute price change 0.025 or higher1-hour price change 0.048 or higherDistance from the day's average price 0.034 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.7312 ≤ -0.73 Book capture feature.book_source native native Compression · 4h feature.candle_compression_4h 2.756 ≥ 2.7 Cascade clustering feature.cascade_clustering_index 0.5145 ≥ 0.51 Depth capture feature.depth_source live live 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 25.98 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 655 12 to 720 OI change magnitude score feature.oi_velocity_pctrank 0.9995 ≥ 0.99 Return · 15m feature.ret_15m 0.02536 ≥ 0.025 Return · 1h feature.ret_1h 0.04815 ≥ 0.048 VWAP distance · day feature.vwap_dist 0.03407 ≥ 0.034
Two other reading times we tried 97 and 19 matches
15 minutes before (21:45): order book tilt 0.67 or higher, book capture is native, open interest change rank 0.99 or higher.
Book imbalance · top levels ≥ 0.67 and Book capture native and OI change magnitude score ≥ 0.99
97 matches: price was 2% or more higher after 30 minutes in 16 of 97 (16.5%), and 2% or more lower in 5 of 97 (5.2%).
Of the 97 matches, 65 came before the rise began, 3 during it and 29 after it.
1 hour before (21:00): book capture is native, 4-hour range against usual 2.7 or higher, containment (15m) is inside.
Book capture native and Compression · 4h ≥ 2.7 and Containment · 15m inside
19 matches: price was 2% or more higher after 30 minutes in 6 of 19, and 2% or more lower in 1 of 19.
Of the 19 matches, 10 came before the rise began, 5 during it and 4 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 21:59: the narrowest set with at least 30 matches before the rise.
Picked after the rise, on one market; the 95 matches came on 29 of 30 days, 3 during the rise.
Hourly candles around the risefull context, lead-up, move
The 22:00 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
Multiple recorded sectors: sector_crypto, sector_defi. Choose one explicitly.
Each opens Review the test; nothing runs until you press Run.
Running needs a free account and uses your allowance; you see the cost first.
Starting defaults and coverage
Starting defaults: 2026-08-23 to 2026-09-22 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.