Sample Report · Machine Learning

Model Evaluation Report — Sample

What an honest model evaluation looks like before a go-live decision — baseline first, performance by segment, the failure analysis, the limitations section, and a recommendation that names its conditions.

Markdown. No sign-up, no email.

This is an illustrative example. The model, figures and findings are composed to show the shape of an honest evaluation, not drawn from a named engagement.

Model: Delivery delay prediction v1.4 Prepared by: _______ Date: _______ Decision requested: approve for production use in the operations queue

1. Summary#

The model predicts whether an order will miss its promised delivery date, 24 hours ahead.

Recommendation: approve, for the ranked-queue use case only, with monitoring in place before go-live. It is not suitable for automated customer notification, for the reason in §5.

Recall (missed deliveries found)0.71
Precision0.64
Trivial baseline recall0.09 (base rate)
Business threshold agreed beforehandrecall ≥ 0.60

2. Baseline first#

ApproachRecallPrecision
Always predict "on time"0.00
Existing rule (no scan in 18h)0.440.51
This model0.710.64

The existing rule is the honest comparison, not the do-nothing baseline. The model finds roughly 27 percentage points more of the delays that occur, at better precision.

3. Method#

  • Split: by time. Trained to 31 March, validated April, tested May onwards
  • Test set used once, at the end
  • Features verified answerable as of the prediction timestamp
  • Leakage review completed; two features removed (both populated after delivery)
  • Results reproducible from a clean run; seed and library versions pinned

4. Performance by segment#

Aggregate figures hide the thing that matters.

SegmentVolume shareRecallNote
Standard domestic68%0.78strongest
Next-day domestic14%0.69
International11%0.41weak
Bulk / palletised5%0.33very weak
New customers (<30 days)2%0.38little history

The model is substantially worse on international and bulk shipments — under half the delays found — and those are the consignments where a delay costs most.

This is the finding that shaped the recommendation.

5. Failure analysis#

Where it fails: consignments with sparse tracking history. The model leans on scan-event frequency, and carriers on international and bulk routes scan less often. Absence of a scan means "late" domestically and "normal" internationally, and the model has not learned that distinction well.

How it fails: silently and confidently. A missed prediction is indistinguishable from a correct "on time" call.

Why this rules out customer notification: telling a customer their delivery is late when it is not, at 0.64 precision, means roughly one in three notifications is wrong. For the internal queue that is acceptable — an operator checks. For a customer message it is not.

6. Limitations#

  • Trained on 14 months. No full peak season in the training window; December behaviour is unproven
  • Two carriers added in April are under-represented
  • Assumes current scan-event frequency; a carrier changing its scanning practice degrades this silently
  • Not evaluated for fairness across customer segments — not obviously relevant here, not checked

7. Cost and latency#

Inference cost£0.0004 per prediction
At current volume~£118/month
p95 latency240 ms
Retraining~4 hours, monthly

8. Conditions of approval#

  1. Used to rank the operations queue, never to notify customers automatically
  2. International and bulk consignments flagged as low-confidence in the interface
  3. Outcome capture in place before go-live, so production accuracy is measurable
  4. Alert if weekly recall falls below 0.60
  5. Reviewed after the first December, before which peak behaviour is unknown

9. What would change this recommendation#

Better recall on international and bulk — most likely from carrier scan data rather than from model changes. If that data becomes available, re-evaluate; the current ceiling is a data limitation, not a modelling one.


Why this report is shaped this way. It leads with the baseline, reports by segment rather than in aggregate, states where and how the model fails, and makes a recommendation with named conditions. A report that gives a single accuracy figure and a recommendation invites approval without any of the information that should qualify it.

See machine learning and the model review checklist.

Back to Machine Learning