Crypto Market Regimes (Short-term) — Quant Regime Probabilities

Current Market Probabilities

Where will the market be in 24 hours? — probability across five outcomes, left = falls, right = rises

10% Strong fall

22% Mild fall

33% Sideways

24% Mild rise

12% Strong rise

▼ MARKET FALLSMARKET RISES ▲

Tomorrow's likely range — 1,000 simulations of the next 24 hours

Worst likely

-4.5%

only 5% of runs end lower

Most likely

+0.1%

the median outcome

Best likely

+4.4%

only 5% of runs end higher

median +0.1%

-4% -2% 0 +2% +4%

Simulations are balanced: half of the 1,000 runs finish between -1.5% and +1.8%. The wide band covers 90% of simulated outcomes, the bright band the middle 50%; the marker is the median.

The 6 regimes

Every market hour gets sorted into one of these six states. Each implies a different way to trade — or not trade.

Strong Trend (Bull)

Sustained directional move up, positive funding, OI expanding.

Playbook: Trend-following ON, mean-reversion OFF

Whole market: 21% of the time since 2019, typically lasting ~3 days at a stretch.

Strong Trend (Bear)

Sustained downtrend, negative funding, OI expanding on the short side.

Playbook: Short trend ON, long momentum OFF

Whole market: 13% of the time since 2019, typically lasting ~2 days at a stretch.

Range / Low Volatility

Low ATR, choppy funding, tight OI range.

Playbook: Mean-reversion ON, trend OFF

Whole market: 27% of the time since 2019, typically lasting ~2 days at a stretch.

Choppy High Volatility

High ATR, no clear direction, elevated liquidations.

Playbook: Reduced size, breakout confirmation required

Whole market: 9% of the time since 2019, typically lasting ~1 day at a stretch.

Volatility Spike

Sudden volatility expansion, liquidation cascade, funding extremes.

Playbook: Pause all / minimal scalp only

Whole market: 8% of the time since 2019, typically lasting ~3 days at a stretch.

Squeeze

Low-volatility compression preceding expansion.

Playbook: Breakout algos primed, directional bet sizing up

Whole market: 23% of the time since 2019, typically lasting ~3 days at a stretch.

What this model would have said, 2019 → now

The live model, run over its full training history — weekly market regime, no hindsight relabeling. Every major crash and bull run is labeled by the exact model serving this page.

COVID crash

2021 bull run

LUNA collapse

FTX collapse

2024 ETF bull

Yen-carry shock

Oct-2025 crash

2020202120222023202420252026

Strong Trend (Bull) · 21% of the time Strong Trend (Bear) · 13% of the time Range / Low Volatility · 27% of the time Choppy High Volatility · 9% of the time Volatility Spike · 8% of the time Squeeze · 23% of the time

Same model, same features, no hindsight relabeling — full daily series via GET /api/v1/quant/timeline.

Per-coin regimes — top Hyperliquid perps by open interest

Each coin gets its own read, conditioned on the whole-market state — SOL can be coiled in a squeeze while the market drifts sideways. Direction numbers are unlocked on the top 3 coins; Pro unlocks all ~177 perps via the API.

BTC

Range / Low Volatility

model is 98% sure

next 24h: ⇄ balanced odds

ETH

Strong Trend (Bear)

model is 53% sure

next 24h: ⇄ balanced odds

HYPE

Squeeze

model is 68% sure

next 24h: ⇄ balanced odds

SOL

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ZEC

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

LIT

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

XRP

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

AAVE

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

PUMP

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

NEAR

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

LINK

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

XMR

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

BNB

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

DOGE

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ADA

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

TAO

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ENA

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

SUI

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

MON

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

UNI

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

XPL

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

PAXG

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ZRO

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

FARTCOIN

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

WLD

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

VVV

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ASTER

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

kPEPE

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

TRX

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

AVAX

Strong Trend (Bull)

model is ??% sure

next 24h: ▲ ??% rise odds

ONDO

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

KAITO

Volatility Spike

model is ??% sure

next 24h: ▲ ??% rise odds

WLFI

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

GRAM

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

LDO

Strong Trend (Bear)

model is ??% sure

next 24h: ▲ ??% rise odds

LTC

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

JTO

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

ETHFI

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

TRUMP

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

GRASS

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

XLM

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

AERO

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

CRV

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

JUP

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

PENDLE

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

VIRTUAL

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

PURR

Squeeze

model is ??% sure

next 24h: ▲ ??% rise odds

DOT

Range / Low Volatility

model is ??% sure

next 24h: ▲ ??% rise odds

Unlock per-coin probabilities for all ~177 Hyperliquid perps → Pro

Every probability, broken out — live BTC

The full probability object behind one coin, as readable bars: where price goes, how violent it gets, liquidation pressure, funding, open interest, and which regime comes next.

Direction (next 24h) confidence 11%

Strong fall 6%

Mild fall 22%

Sideways 39%

Mild rise 24%

Strong rise 9%

Volatility (next 24h) confidence 4%

Low 44%

Medium 36%

High 21%

Liquidation risk (next 24h) confidence 4%

Low 44%

Medium 36%

High 21%

Funding direction (next 24h) confidence 0%

Falls 29%

Stable 36%

Rises 36%

Open interest (next 24h) confidence 1%

Contracting 28%

Neutral 39%

Expanding 33%

Regime transitions (next 24h) confidence 23%

Stays Range / Low Volatility 42%

→ Squeeze 25%

→ Strong Trend (Bull) 17%

→ Strong Trend (Bear) 13%

This exact JSON, every 15 minutes, for every coin

Live BTC probability object — including the explain block: feature z-scores, raw state posteriors, the hysteresis rule, raw-vs-calibrated confidence. If you can't audit a probability, you shouldn't trade on it.

{
  "scope": "BTC",
  "symbol": "BTC",
  "timestamp": "2026-08-02T07:09:27.154000Z",
  "horizon": "24h",
  "regime": {
    "label": "range_low_vol",
    "name": "Range / Low Volatility",
    "id": 2,
    "confidence": 0.975,
    "confidence_raw": 0.9988,
    "label_raw": "range_low_vol",
    "candles_in_regime": 11
  },
  "probabilities": {
    "directional": {
      "strong_down": 0.0648,
      "mild_down": 0.2199,
      "flat": 0.3866,
      "mild_up": 0.2361,
      "strong_up": 0.0926,
      "confidence": 0.106
    },
    "volatility": {
      "low": 0.4384,
      "medium": 0.355,
      "high": 0.2066,
      "confidence": 0.0397
    },
    "funding": {
      "falls": 0.2857,
      "stable": 0.3595,
      "rises": 0.3547,
      "confidence": 0.0048
    },
    "liquidation_risk": {
      "low": 0.4384,
      "medium": 0.355,
      "high": 0.2066,
      "confidence": 0.0397
    },
    "open_interest": {
      "contracting": 0.2847,
      "neutral": 0.3866,
      "expanding": 0.3287,
      "confidence": 0.0071
    },
    "regime_transitions": {
      "stays_same": 0.4241,
      "to_squeeze": 0.247,
      "to_strong_trend_bull": 0.1661,
      "to_strong_trend_bear": 0.1285,
      "confidence": 0.226
    }
  },
  "meta": {
    "model_version": "2.0.0",
    "model_family": "hmm",
    "last_retrain": "2026-06-20T17:03:26.739290Z",
    "data_staleness_ms": 4167154,
    "feature_coverage": 1.0,
    "insufficient_history": false,
    "status": "ok",
    "backfilled": false
  },
  "explain": {
    "features": {
      "ret_1h_z": -0.6199319336900121,
      "ret_24h_z": 0.44871925961324527,
      "vol_ewma_z": -0.4434905929507296,
      "vol_ratio_log": -0.9727404748929278,
      "bb_width_pctile": 0.18333333333333313,
      "rel_btc_24h_z": 0.0,
      "funding_z": 0.42242817360077356,
      "trend_7d": -0.2000798504342393
    },
    "label_posteriors": {
      "strong_trend_bull": 0.00079,
      "strong_trend_bear": 0.00036,
      "range_low_vol": 0.99879,
      "choppy_high_vol": 0.0,
      "vol_spike": 0.0,
      "squeeze": 0.00007
    },
    "hysteresis": {
      "rule": "challenger > incumbent + 0.1 for 2 bars, or challenger > 0.7 instant, or incumbent < 0.1 (collapsed)",
      "pending_challenger": null
    },
    "calibration": {
      "confidence_raw": 0.9987851268408731,
      "confidence_calibrated": 0.975,
      "scale_applied": 1.0
    },
    "thresholds_resolved": {
      "sigma_1h": 0.002821,
      "mild": "±0.35%",
      "strong": "±1.38%"
    }
  }
}

GET /api/v1/quant/coins/BTC — get a Pro key →

What this model is — and what it isn't

We retrospectively scored every hourly regime call this model would have made (56,000+ hours, 2020 → now) against what BTC, 16 major alts and all ~175 Hyperliquid perps actually did next. Here's the honest read — because a probability you can't audit is a probability you shouldn't trade.

It identifies the market state — reliably

The HMM is a nowcast: it tells you which regime the market is in right now, within hours of a state change. During vol_spike, 73–79% of coin-hours across the entire Hyperliquid universe saw elevated volatility over the next 24h. Use it to size positions, widen stops and set liquidation buffers across your whole book.

It routes strategies — measurably

A 24h-momentum strategy that is flat over all hours splits sharply by regime: mean-reversion worked during bear and vol_spike on every dataset we tested (BTC, majors, full HL universe), momentum leaned positive in squeeze. Long-BTC-only-during-bull historically halved max drawdown vs a 200-day trend filter at similar return. Use the regime to pick which strategy runs, not which way to bet.

It does NOT predict direction

P(BTC up next 24h | bull) was 52.8% vs a 52.1% base rate — no edge. And don't short bear: by the time the model flips bearish, ~−2.5% has already happened and the next 7 days averaged positive. The historical timeline above matches price so well because the regime is computed from the move already underway — those bands are recognitions, not calls. No regime model (ours or anyone's) predicts short-horizon direction; vendors who claim otherwise aren't showing you their base rates.

Every number above is reproducible: pull the full point-in-time regime history via GET /api/v1/quant/regimes/history and score it yourself. Calibrated forecast heads (volatility, liquidation-cascade risk, squeeze resolution) with published scorecards are the next release on this engine.

LAUNCH PREVIEW This page is a free launch preview — data is ~30-min delayed. The API is real-time.