Technical Note · 09 Jun 2026

Why your model looks better than it is

A validation score is a measurement of your evaluation setup at least as much as it is a measurement of your model.

Format
Technical Note
Reading time
6 min
Published
09 Jun 2026
Desk
DevCSE Applied ML Desk

01

Leakage is usually structural

It rarely arrives as a duplicated row. It arrives as a feature computed over the full dataset, a target encoded before the split, or a time series shuffled at random. Build the split first and compute everything after it.

02

Aggregate metrics hide the failures that matter

A model can post an excellent overall score while failing completely on the slice your users care about. Report per-slice error from the first experiment, not after the first complaint.

03

Fix the seeds, then vary them

A single run gives you a point estimate with unknown variance. Repeat across seeds and report the spread; a two-point improvement inside four points of seed noise is not an improvement.

04

Write the evaluation before the model

Deciding what counts as success after seeing results is how a benchmark stops being a benchmark. Specify the metric, the slices and the acceptance threshold in advance.