Auditable formula · fictional example
On-Time Delivery Rate: Formula, Promise Window, and AI Pilot
Direct answer: On-time delivery rate divides deliveries completed inside the agreed promise window by all eligible completed deliveries. The promise, cutoff, timezone, exclusions, and proof event must be frozen before the pilot.
Numerator
7,360 deliveries inside the promise window
Denominator
8,000 eligible delivered orders
Fictional result
92.0% on-time delivery
Formula and worked example
On-time delivery rate = on-time delivered orders / eligible delivered orders x 100
Fictional example: 7,360 on-time deliveries / 8,000 eligible deliveries x 100 = 92.0%.
The numbers demonstrate the calculation only. They are not a benchmark, forecast, target, vendor result, or promise.
Four-step measurement method
- Step 1
Define the customer promise and timestamp used to judge completion.
- Step 2
Freeze legitimate exclusions before seeing pilot results.
- Step 3
Count eligible completed deliveries and those inside the window.
- Step 4
Review the rate by lane, carrier, service level, and delay reason.
Checks before comparison
- Promise source is recorded
- Timezone and cutoff are stable
- Customer-requested delays are classified
- No post-result exclusion changes
Common measurement errors
- Using dispatch time instead of delivery completion
- Changing the promise window
- Optimizing distance while late delivery rises
Attribution boundary
A change in this metric does not prove that AI caused it. Compare a frozen baseline and controlled pilot, then inspect route mix, distance, fuel, tolls, carrier rates, service level, package profile, promotions, weather, exclusions, and policy changes. Protect service and failure metrics while evaluating cost.
Frequently asked questions
Can a cheaper route plan still be worse?
Yes. If cost falls while on-time performance or delivery success deteriorates, the plan shifted cost into service failure rather than proving a better operation.
Does this metric prove that AI caused the result?
No. A before-and-after change can also reflect route mix, distance, fuel, carrier rates, package profile, promotions, weather, exclusions, or operational policy. Use a controlled pilot and inspect segments before attributing causality.