Skip to content

Model Training & Adaptation

ROC curve

Receiver operating characteristic

A chart showing the tradeoff between correct detections and false alarms as a system's decision cutoff changes.

Example

A team compares settings that catch more cases but also raise more false alarms.

Why people use it

It shows how catching more positive cases can also increase false alarms.

What you'll hear

“What happens to false alarms if we catch more real cases?”

What this means for you

Choose a cutoff based on the practical cost of each kind of mistake.

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 two curves cross?
Yes. One system can be better at one balance of detections and false alarms but worse at another.
Does the curve choose the best operating point?
No. That choice depends on the practical cost of missed cases and false alarms.
Can the same curve lead to different choices in different jobs?
Yes. The consequences of mistakes can justify different cutoffs.

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