Live condition · historical base rate

Book imbalance above its 95th percentile

Order-book imbalance is reading above its own trailing 95th percentile for this market.

Firing now (provisional, current bucket)

The live read is not yet enabled. This surface reports the historical base rates below; the firing-now list turns on when the live evaluator is connected.

What has happened when it held

Historically, when Book imbalance above its 95th percentile held (173,551 occurrences in the scanned window, 164,551 with a computable 24h horizon), the market reached +5% within 24h in 46,867 of 164,551 (28.5) and drew down 10%+ in 7,428 of 164,551 (4.5). Maximum favorable (MFE) and maximum adverse (MAE) excursions, both computed forward.

Outcome distribution

WHAT FOLLOWED · ALL 173,551 MATCHES

143,795 of 168,931 (85.1%) reached +0% or more within 1 hour · smallest move size with matches, picked for you

Pick a window and a move size: how often did a move at least that big follow?

WINDOWMOVE SIZE

🔒 Measured after every match, never by keeping winners. 168,931 of the matches have a complete 1 hour forward; the other 4,620 are too recent to know.

What are MFE and MAE?

Why 7 days can show fewer than 1 hour: a match too recent for a complete 7 days is left out of that count entirely, even if it already reached the level within 1 hour. The two counts cover different sets of matches.

When they happened - one bar per UTC day, all 173,551 matches

About 5,598 a day, on 31 of 31 days: spread through the record rather than one event.

Where the next 30 minutes landed - 162,930 measured, 10,621 too recent

Forward 30-minute returns across 162,930 matches: close to an even split, which is what a coin flip looks like.

How to read a distribution

Upside reached · 24hThe most price moved up within 24h of each occurrence: a high-water mark, never a close. 164,551 with a complete 24h.

Drawdown · 24hThe worst price moved against within 24h of each occurrence: the deepest point, never the close. 164,551 with a complete 24h.

Versus baseline

Historically, when any eligible minute in the window (baseline) held (29,796,213 occurrences in the scanned window, 26,015,636 with a computable 24h horizon), the market reached +5% within 24h in 7,560,584 of 26,015,636 (29.1) and drew down 10%+ in 1,614,440 of 26,015,636 (6.2). Maximum favorable (MFE) and maximum adverse (MAE) excursions, both computed forward.

By market

Markets where this condition occurred often enough in the window to carry its own statistically meaningful receipt:

Check our work: the key that re-runs this exact count (q#7a3dc45e)

grammar: research_query.v2
normalization: archive_normalization.v1
feature library: feature_defs.v1
dataset revision: 8904ef0442c6f623ec772df2b59d7baf1e49aaa808b5b11ac31546605549e3bb
query hash: 7a3dc45e2e09e5753fba3df6282cc737f9ea0be517fdf3bece20b6cab69c44f3
scanned window: 2026-08-19T00:00:00.000Z to 2026-09-18T00:00:00.000Z (UTC)

Same key, same bytes. This receipt reruns; it does not retell. When the record grows, the dataset revision changes and says so.

Re-run this yourself, over the API or from an AI agent

This is the exact search definition behind the receipt. Send it to the key-authed research API (or the MCP research tool) and compare the bytes: a cached rerun is free.

{
  "schema_version": "research_query.v2",
  "normalization_version": "archive_normalization.v1",
  "feature_version": "feature_defs.v1",
  "target": "record_occurrences",
  "where": {
    "all": [
      [
        "feature.book_imbalance_pctrank",
        "gte",
        0.95
      ],
      [
        "times.anchor_time",
        "between",
        [
          "2026-08-19T00:00:00.000Z",
          "2026-09-18T00:00:00.000Z"
        ]
      ]
    ]
  },
  "sort": [
    "times.anchor_time",
    "desc"
  ],
  "page": {
    "limit": 50,
    "cursor": null
  }
}

curl -s https://app.edgedepth.com/api/v1/research/query \
  -H 'authorization: Bearer $EDGEDEPTH_API_KEY' \
  -H 'content-type: application/json' \
  -d '{"schema_version":"research_query.v2","normalization_version":"archive_normalization.v1","feature_version":"feature_defs.v1","target":"record_occurrences","where":{"all":[["feature.book_imbalance_pctrank","gte",0.95],["times.anchor_time","between",["2026-08-19T00:00:00.000Z","2026-09-18T00:00:00.000Z"]]]},"sort":["times.anchor_time","desc"],"page":{"limit":50,"cursor":null}}'

How to read this

Counts ship with denominators: occurrences across the eligible symbol-buckets scanned. A rate is over the occurrences with a computable horizon (present), never the total.
Absent is absent. When a feature was not warm at a minute, that bucket leaves the denominator and is reported; it is never coerced to zero.
This selects a setup, never its outcome. The grammar forbids filtering on what followed (OUTCOME_IN_PREDICATE), so the distribution below is over every occurrence, not a survivorship-picked subset.

Occurrences are observed examples in a selected archive, not a guarantee. Outcomes are computed forward from each anchor and are descriptive, never a filter and never a prediction. Nothing here is trading advice.