Public forecast documentation
Normalized forecast error explained
The deployed public card's implementation captured on 2026-09-11 defines SiCierto's predicted-price-normalized mean absolute error percentage. This is a historical implementation observation, not a current-performance guarantee.
Historical audit snapshot created 2026-09-10 — not a live/current forecast
Observed deployed-card definition
SiCierto predicted-price-normalized mean absolute error percentage = (100 / n) × Σᵢ₌₁ⁿ |Aᵢ − Pᵢ| / Pᵢ
The deployed public card captured on 2026-09-11 calculates a row-level ratio for each asset and horizon over a rolling 30-day window keyed by target_at, retaining rows with non-null target_at and actual. Here A is actual price, P is predicted price, and n is the included row count for that card. The result is multiplied by 100 and displayed to one decimal place with toFixed(1).
This is SiCierto's custom predicted-price-normalized mean absolute error percentage: it is not standard MAPE, which uses actual price as its denominator; it is not raw-unit MAE or a ratio of means. The captured deployed implementation is authoritative for the metric displayed by that card at capture. This capture is not an immutable released archive or a guarantee of current behavior.
The formula assumes P > 0 (a positive predicted price). The captured production implementation has no zero or non-positive predicted-price guard, so an invalid denominator can produce an invalid or undefined ratio; this page does not add a guard or silently substitute a new algorithm. No normalized-error value is published here. Use the aggregate forecast accuracy evidence page for the broader metric inventory and its limitations.
Normalized-error evidence boundary
The retained September 10, 2026 audit evidence contains 56 total SOL forecast rows and 40 resolved rows. Their observed target span is 2026-09-07T07:14:30Z–2026-09-10T10:59:20Z; this is row-derived context, not a prespecified evaluation window.
The figures below are a dated audit snapshot, not a live feed. The retained rows support arithmetic for the displayed Brier and coverage values, but they are point-in-time API evidence rather than an immutable research dataset. The snapshot cannot establish profitability, statistical significance, non-overlapping holdout performance, or predictive superiority.
Data provenance and export status
The statistics shown here come only from the forecast audit snapshot created 2026-09-10. Current values remain on the external live product. The local scheduled-worker forecast table is a distinct implementation and is not represented as that external production feed.
Citation-ready public export status: NOT READY. The retained historical evidence contains 56 total SOL forecast rows and 40 resolved rows, with resolved horizon counts of 6h n=13, 12h n=12, 24h n=9, 48h n=6 and observed target span 2026-09-07T07:14:30Z–2026-09-10T10:59:20Z. These are point-in-time observations, not an immutable issued-and-resolved archive, complete history, or prespecified evaluation window. A current public feed may expose rows, but it is not an immutable versioned research archive. Metrics calculated from a changing feed are not automatically comparable to this dated snapshot. A research export would need versioned records with forecast ID, asset and venue, UTC issue and target timestamps, horizon, point prediction, interval bounds, direction probability, model version, outcome source, observed price, resolved-at time, scoring-rule version, and content hash. No research export is available from these pages.
The existing Dataset JSON-LD preserves the audit date rather than implying freshness.