Advanced – AI & ML Testing
Accuracy (ML) – ISTQB Definition
Last Updated: July 12, 2026 · SoftwareTestPilot QA Team
Official ISTQB Definition
A classification metric equal to the fraction of predictions that are correct.
In simple words
The percentage of predictions the model got right overall.
Exam tip
Accuracy misleads on imbalanced datasets — prefer precision, recall, F1 for skewed classes.
Related terms
Practice this term in the ISTQB Mock Test
40 CTFL v4.0 questions, 60-minute timer, instant scoring and chapter-wise breakdown.
Practice in Mock Test