HOMEUSDT rose 78% into Aug 2. The record covers the whole lead-up.

Move window: 2026-07-31 00:00 to 2026-08-02 18:00 UTC. The record for HOMEUSDT currently ends 2026-08-03 00:00 UTC.

Book imbalance · top levels ≥ 0.98 and Book imbalance percentile ≥ 0.94 and Cascade clustering ≥ 0.51

feature.book_imbalance + feature.book_imbalance_pctrank + feature.cascade_clustering_index

Read at 15 minutes before the move.

Minutes like this appeared only 6 times in the 43,201 minutes searched. What followed leaned down: 4 of the 6 matches with a complete 30 minutes forward fell (67%).

Of the 6 fires, 4 came before the move began and 2 happened while it was already under way. A fire during the move sees it; it does not telegraph it.

About 0.2 a day, on 4 of 31 days: spread through the record rather than one event.

q#f00b8d88 @ dataset b91f2197

WATCH FOR THIS Watch the ignition replay

Best supported: Book imbalance · top levels ≥ 0.98 and Book imbalance percentile ≥ 0.94 and Cascade clustering ≥ 0.51, the combination with the most fires before the move began.

Opens this exact search in the research tool. Nothing runs until you confirm it there, and arming it as an alert sends a message when it next becomes true.

Picked in hindsight: the counts include every other time these readings appeared, not just this move.

What the minutes before it looked like

Where these readings were taken

Hourly candles. The marked lines are the minutes the readings came from: 1 minute, 15 minutes, 1 hour, 4 hours and 24 hours before the move began. Every one of them sits before the move, never inside it.

A reading stands out when it sits outside the range it usually holds. The rules are fixed: the same ones the moment reader on the research page uses.

At 1 minute before the move, 3 of the 33 readings stood out. 2026-07-30 23:59 UTC

READING	BEFORE THE MOVE	SEARCHES FOR
Cascade clustering feature.cascade_clustering_index	0.5154	≥ 0.51
Minutes to funding feature.mins_to_funding	1	≤ 1
Taker buy share · 15m feature.taker_buy_ratio_15m	0.2755	≤ 0.28

At 15 minutes before the move, 4 of the 33 readings stood out. 2026-07-30 23:45 UTC

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	0.9893	≥ 0.98
Book imbalance percentile feature.book_imbalance_pctrank	0.9495	≥ 0.94
Cascade clustering feature.cascade_clustering_index	0.5154	≥ 0.51
Minutes to funding feature.mins_to_funding	15	≤ 15

At 1 hour before the move, 5 of the 33 readings stood out. 2026-07-30 23:00 UTC

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	-0.9302	≤ -0.93
Book imbalance percentile feature.book_imbalance_pctrank	0.9616	≥ 0.96
Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m	bearish	bearish
Upper wick · 15m feature.candle_upper_wick_15m	0.625	≥ 0.62
Cascade clustering feature.cascade_clustering_index	0.5154	≥ 0.51

At 4 hours before the move, 3 of the 33 readings stood out. 2026-07-30 20:00 UTC

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	-0.5773	≤ -0.57
Cascade clustering feature.cascade_clustering_index	0.5154	≥ 0.51
VWAP distance · day feature.vwap_dist	-0.03291	≤ -0.032

At 24 hours before the move, 7 of the 33 readings stood out. 2026-07-30 00:00 UTC

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	0.7239	≥ 0.72
Containment · 15m feature.candle_containment_15m	inside	inside
Cascade clustering feature.cascade_clustering_index	0.5356	≥ 0.53
Minutes to funding feature.mins_to_funding	0	≤ 1
Realized vol percentile feature.realized_vol_pctrank	0.9732	≥ 0.97
Return · 1h feature.ret_1h	0.03048	≥ 0.03
VWAP distance · day feature.vwap_dist	0.02133	≥ 0.021

Also counted

This is not a similarity search. Each count matches the exact readings above and nothing else.

Cascade clustering ≥ 0.51 and Minutes to funding ≤ 1 and Taker buy share · 15m ≤ 0.28

feature.cascade_clustering_index + feature.mins_to_funding + feature.taker_buy_ratio_15m

Read at 1 minute before the move.

Minutes like this appeared only 1 time in the 43,201 minutes searched. What followed leaned up: 1 of the 1 matches with a complete 30 minutes forward rose (100%).

Its one fire came before the move began.

About 0 a day over 31 days, but 2026-07-30 alone holds 100% of them: this is close to a single episode.

q#5f82fda2 @ dataset b91f2197

Book imbalance · top levels ≤ -0.93 and Book imbalance percentile ≥ 0.96 and Sweep + reclaim · 15m bearish

feature.book_imbalance + feature.book_imbalance_pctrank + feature.candle_sweep_reclaim_15m

Read at 1 hour before the move.

Minutes like this appeared only 2 times in the 43,201 minutes searched. What followed leaned up: 2 of the 2 matches with a complete 30 minutes forward rose (100%).

Of the 2 fires, 2 came before the move began; none were during it.

About 0.1 a day over 31 days, but 2026-07-21 alone holds 50% of them: this is close to a single episode.

q#c39ae045 @ dataset b91f2197

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.