LIVE·SANTOS $1.2M demurrage accruing·58 anchored · median 50h·congestion $4.1/t·12.4Mt cargo at anchor·PARANAGUÁ $22.7M·45 ports · as of 2026-08-01 10:20 UTC
// VERIFIED ACCURACY

We publish our error.
Ask anyone else to do the same.

Coverage is easy to advertise. Accuracy isn't. Below is how close our berth-wait forecasts land against real berthings — per port, recomputed monthly, straight from the backtest. Numbers here render from the public /v2/meta/validation endpoint.

WAIT-WINDOW P50 · MEDIAN ABSOLUTE ERROR (HOURS) · LOWER IS BETTER
PORT ATRACAI P50PORT-MEDIAN BASELINECALLSVERDICT
Santos88.287.02,745baseline serves
Paranaguá119.7142.9882BEATS
Vitória63.763.0442baseline serves
Itaqui125.3137.9823BEATS
Rio Grande59.057.9326baseline serves

Time-based train/test split (never random for time-series). "Verdict" = beats the naïve baseline a customer could compute for free.

CALIBRATION

P10–P90 coverage

Our 80% band should contain the actual wait ~80% of the time. At Santos it currently holds 74% — we report the gap honestly and widen the band where it's short.

WHAT WE DON'T PREDICT

The honest column

We do not publish numbered FIFO queue positions (Santos FIFO tested worse than a coin flip) or hour-of-day claims where timestamps look rounded. If a model fails its gate, it does not ship.

FRESHNESS

Last validated

2026-08-01 10:20 UTC

Predictions refresh every 30 minutes; accuracy is recomputed against live actuals and republished monthly.

73–87% of calls berth inside our P10–P90 window.*

*Measured coverage by port (STS 73%, ITJ 87%), published live at /accuracy. The point isn't that we're perfect — it's that we tell you exactly how imperfect, in public, before you pay.

Request access