Four surfaces, one regulatory posture.
Every endpoint returns identical analytics for all entitled customers. Tiers gate latency, history depth, exports, and rate limits — not signal content.
Fresh signal onsets priced as exit-at-onset hedge windows — current one-leg cost vs backtest adverse-move priors, with live alert precision and auditable arm provenance.
Systemic breadth: share of the tracked universe elevated per time bucket, on a 0–100 scale with trailing z-scores and category attribution.
Hours where an unusually broad set of markets fired at once relative to the trailing baseline — relative episodes, not fixed thresholds.
Freshness vs SLA, universe coverage, trailing live hedge-alert precision, and per-model calibration status including regression-guard verdicts.
At each fresh rules-arm onset we price an exit-at-onset hedge window:
compare the current one-leg exit cost (half-spread + slippage) to the backtest mean adverse |Δprob| excursion for that arm.
Each opportunity carries trailing live-alert precision, arm provenance (n_trades, t-stat, edge vs naive), and an
actionable filter — a standardized data flag, not a recommendation.
Change-point and other demoted families are excluded from customer REST surfaces by default.
enterprise_data adds cursor-paginated hedge ledger, extended stress history,
calibration exports, analyst briefing CSV, and async bulk exports under /api/v1/enterprise/*.
Standardized, impersonal market analytics for informational purposes only — not trading, investment, or hedging advice, and not a recommendation to transact in any market. Outputs are identical for all customers and are not tailored to any person's positions or circumstances (we never ingest customer positions, inventory, or P&L). Past performance, including live scored history and backtests, does not guarantee future results. All decisions remain yours.