DATA VENDOR · QUANTITATIVE MARKET INTELLIGENCE

Live regime, risk, and allocation signals from a model-driven research stack.

Quark Research publishes daily and intraday signals — regime probabilities, factor-structure reads, alpha attribution, and per-asset weights — delivered via versioned REST, WebSocket, and CSV. Suited to systematic desks, multi-asset overlays, and risk teams that need a second-opinion architecture on top of conventional tools.

+0.00% Live ensemble · since inception
+0.00pp Alpha vs SPY
-- Sessions tracked
Frequency
Daily + intraday
Universe
~30 large-cap US + 4 ETFs
History
Point-in-time, 60+ months
Format
REST / WebSocket / CSV
License
Per-seat / per-AUM
Available datasets

Six API surfaces, one signal stack.

Every dataset is point-in-time-reproducible, versioned under /api/v1/, and carries explicit deprecation headers when surfaces change. Webhooks deliver push events whenever a regime, signal, or weight crosses a threshold.

REGIME · DAILY

Regime probability distribution

Posterior probabilities for risk-on / neutral / risk-off / crisis, plus the dominant classifier and a confidence score. Daily refresh, intraday on stress events.

GET /api/v1/regime-probability
CURRENT SIGNAL

Live composite signal

Regime label, tail-risk read, recommended allocation summary, and risk parameters for use in overlays. Compact JSON suited to webhook delivery.

GET /api/v1/signals/current
RAW · INSTITUTIONAL

Unfiltered signal stack

Full per-signal contributions across the 18-factor stack: regime score, factor stability, mispricing intensity, correlation persistence, and ten more orthogonal reads.

GET /api/v1/signals/raw
HISTORY · 730 DAYS

Time-series & CSV

Replay any signal back through the available history window. JSON for systems, CSV for spreadsheet ingestion, both with consistent schema.

GET /api/v1/signals/history.csv
POINT-IN-TIME

As-of lookup

Rebuild what the model would have produced at a specific historical timestamp. Designed for backtest reproducibility and walk-forward validation.

GET /api/v1/signals/at?as_of=...
ATTRIBUTION

Alpha decomposition

Per-signal alpha contribution, normalized weights, and rolling attribution windows. Lets risk teams see exactly which signals drove the period's return.

GET /api/v1/alpha/attribution
Integration · 5-minute test drive

Pip install. One call. Live data.

The quark-research Python SDK ships on PyPI under MIT license. Public endpoints (regime, current signal, benchmark) require no key. The institutional surfaces and the unfiltered signal stack require a qk_ token from your tier.

Python · pip install + 3-line example
# pip install quark-research
from quark_research import QuarkClient

client = QuarkClient(api_key="qk_...")  # public endpoints work without a key
print(client.signals_current())
print(client.regime())
cURL · raw HTTP
# Public — no auth required
curl https://api.quarkresearch.cc/api/v1/regime-probability

# Authenticated — institutional tier
curl -H "Authorization: Bearer qk_..." \
     https://api.quarkresearch.cc/api/v1/signals/raw
Diligence pack

Inspect the data before you license it.

A sample report, a sample CSV from the public history endpoint, and the methodology whitepaper — enough to satisfy a portfolio-engineering review without a sales call.

Licensing

Pick a tier. Subscribe in 60 seconds.

All tiers include the regime classifier, weekly publication, and dashboard access where applicable. API access opens at the Automated tier; auto-rebalance at Automated Plus. Cancel any time from the customer portal.

Starter
$5/mo
Email-only. Weekly regime signal + 3-bucket allocation.
  • Weekly regime publication
  • 3-bucket allocation summary
  • Performance vs 60/40
Professional
$49/mo
Email + dashboard. 12-ETF target weights + intelligence report.
  • Everything in Starter
  • Weekly intelligence report
  • 12-ETF target weightings
  • Client dashboard access
Automated
$149/mo
Full REST API. Webhook push. 730-day history. Point-in-time replay.
  • Everything in Professional
  • Versioned REST API + Python SDK
  • Webhook push delivery (sub-200ms)
  • 730-day history + as-of replay
  • 10K API calls / month
Automated Plus
$299/mo
Auto-rebalance. Tail-risk defensive rotation. P&L attribution.
  • Everything in Automated
  • Alpaca auto-rebalance hooks
  • Tail-risk defensive rotation
  • Per-signal P&L attribution
  • 50K API calls / month
Institutional
Custom
Real-time streaming. Custom universe. Dedicated support.
  • Everything in Automated Plus
  • Real-time streaming WebSocket
  • Custom asset universe
  • Unlimited API calls
  • Dedicated support channel
Methodology

A second-opinion architecture, not a replacement.

The signal stack composes a Markov-switching regime classifier with a factor-stability monitor, an order-flow imbalance read, and a tail-risk module that watches the tails of the return distribution rather than its centre. Each component runs independently and combines into a single composite read, with full attribution preserved on every cycle.

Models target one specific failure mode of vanilla quantitative tools: their tendency to flag regime changes after the fact. By tracking the structure of factor returns (not just their level) the architecture sees rotation events earlier in the process, while still anchoring to public benchmarks.

Every published signal is reproducible point-in-time. Methodology paper, full attribution backtests, and a sample data feed are linked below.

Read insights →

Coverage spec

  • Asset classUS equities, FX, rates, commodities
  • Sector breadth11 GICS sectors
  • Factor stack18 orthogonal signals
  • Regimes tracked4 (RISK_ON / NEUTRAL / RISK_OFF / CRISIS)
  • Refresh cadenceDaily close + intraday on stress
  • Webhook latency< 200ms p99
  • SDKPython (PyPI · v1.x)
  • ComplianceVersioned · audited · deprecation-tracked
Use cases

Where the data lands.

Designed for desks that already have a primary quantitative process and want a structurally orthogonal second read.

01 · RISK

Tail-risk monitoring

The crash-barrier and topological-stress reads update before the conventional VIX / credit-spread proxies catch up. Risk teams use them as a leading indicator on the drawdown shield.

02 · ALLOCATION

Portfolio construction

Live regime probabilities feed into dynamic asset-class tilts. The recommended allocation surface is a starting point for an in-house overlay or a direct lift.

03 · STRESS TESTING

Walk-forward validation

Point-in-time signals make it trivial to replay any internal strategy against the live signal stack as a counter-factual — an honest answer to "what would Quark have said two years ago?"

Get started

Pull a sample. Wire the SDK. Subscribe when ready.

Public endpoints are open for evaluation; institutional-tier feeds and the unfiltered signal stack require a license. Live performance, sample reports, and the methodology paper are linked below.