Evaluation & Quality
Confusion matrix
A table showing where a classifier is correct and the types of mistakes it makes.
Example
A confusion matrix separates correct predictions, false alarms, and missed cases by class.
Why it matters
It shows patterns of error that an overall score can hide.
You'll hear it
“The system keeps confusing these two categories.”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does the table need only two groups?
- No. It can show predictions across several categories.
- Can the row and column meanings differ between tools?
- Yes. Check which side represents actual answers and which represents predictions.
- Does a large number on the diagonal always settle performance?
- No. Group sizes and the consequences of off-diagonal mistakes still matter.