THE ACCURACY REPORT

We grade our own homework. Here are the grades.

374,000 test predictions, measured on the most recent three weeks of data the models had never seen. Every claim on this page comes from that held-out test - or from live shipments in transit.

±2 hrs
Average delivery-time error - vs 6.5h for lane averages
81%
Measured hit rate on an 80%-confidence promise
3.7×
Late-warning accuracy vs rule-of-thumb methods
90–97%
Stuck-package discrimination, 6–24h horizons
CALIBRATION

The odds we quote are the odds you get.

Most tools give you a point estimate and hope. We sell calibrated probabilities: when we say a package will arrive within a window 8 times out of 10, it does - measured at 81% against an 80% promise.

We predict delivery windows and late risk - we don't guarantee delivery times. That honesty is the differentiator.

PROMISED VS MEASURED
PROMISED · 80%
MEASURED · 81%
Within one point of perfect calibration, on 374,000 held-out predictions.
METHODOLOGY

How we measure.

HELD-OUT DATA

Models are evaluated on the most recent three weeks of shipments they never trained on - the same test a customer's live traffic poses. No cherry-picked lanes, no retrofit benchmarks.

HONEST BASELINES

We compare against the methods teams actually use - lane averages for ETAs, rules of thumb for late flags - not strawmen. The 3.4× and 3.7× multiples are against those.

CONTINUOUS GRADING

Every prediction is stored and automatically graded against the real outcome when the package delivers. Accuracy claims come from this feedback loop, not a one-time study.

LIVE VALIDATION

Tested on freight that was still moving.

Beyond the held-out test, we ran predictions on live shipments in transit. Every on-time/late call was correct, and the delivery landed inside the predicted window in nearly every case.

CASE · OVERNIGHT INTO RURAL CALIFORNIA

An overnight shipment into a rural California address - the kind lane averages miss badly - called correctly with 9 hours of lead time. Window contained the delivery; on-time call correct.

CUSTOMER STORIES

First enterprise deployment in progress. Until we have their numbers, we show you ours - ask for the live validation data in a demo.

THE DATA FOUNDATION

The carriers' networks, mapped from the outside.

Built and validated on 7 million real shipments and 55 million tracking events across 11 carriers. From tracking data alone - no carrier cooperation required - the models reconstructed:

64,000
carrier facilities located
90,000
lane timings measured
6,300
scheduled sort & departure waves
11
carriers - FedEx, UPS, USPS, OnTrac, LaserShip, regional last-mile
Request demo See what it predicts