Skip to content

Evaluation & Quality

Calibration curve

A chart showing whether predicted chances match how often things actually happen.

Example

Cases predicted near 60% are plotted against how often their outcomes actually occurred.

Why people use it

It shows whether stated chances line up with how often events actually happen.

What you'll hear

“Do the 70% predictions happen about seven times in ten?”

What this means for you

Inspect sample sizes and relevant subgroups as well as the overall curve.

Can you control it?

No

No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.

Common questions

Can a well-matched curve still come from a weak predictor?
Yes. Honest chances do not necessarily mean the system can distinguish difficult cases well.
Why can a small sample make the curve misleading?
A few outcomes can move the apparent rate sharply when there are not many examples.
Can the overall curve hide differences between groups?
Yes. Combining everyone can conceal overconfidence for one group and underconfidence for another.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice