Skip to content
BENIBIX Learn

Accuracy (Machine Learning)

AI📏 Evaluation & BenchmarksClassification Metrics

Also known as Accuracy, Classification Accuracy

The share of a model's answers that are right. Nine right out of ten is 90%.

Think of it like

It is like your score on a spelling test. Get 9 of 10 words right, and you scored 90%.

Example

Lucy's model checks 1,000 X-rays and gets 970 right, so its accuracy is 97%. But only 30 X-rays showed the illness, and it missed 20 of them.

Why it matters

It is a quick first check that anyone can read. Just never let it be the only one.

Definition

Accuracy is the share of a model's answers that are right, out of all its answers. If a model labels 100 photos and gets 90 right, its accuracy is 90%. It is the easiest score to understand, so it is often the first one people look at. But it can fool you when one answer is much more common than the others. Then a model can score high while missing nearly every case that matters.
100 answers: 90 right and 10 wrong, so the accuracy is 90%.

Common mistake

Trusting accuracy when the cases are lopsided. If 99% of cases are fine, 99% accuracy can mean the model learned nothing.

Key takeaways

  1. 1
    Right out of all. One simple share.
  2. 2
    Easy to read. A good first look.
  3. 3
    Lopsided data fools it. Check other scores.

Compare