Ml Functional Performance
ML functional performance is the degree to which a machine learning system correctly performs its intended function according to defined objectives and expected behavior.
“The degree to which an ML model meets ML functional performance criteria.”
(Definition reproduced from the ISTQB Glossary. Copyright belongs to ISTQB.)
View the complete ISTQB GlossaryWhat is Ml Functional Performance?
Unlike traditional software, ML functional performance is evaluated using statistical measures because outputs are based on learned models rather than fixed rules.
Prediction quality: Evaluates how well the model performs intended tasks.
Data dependency: Performance depends heavily on training and evaluation datasets.
Continuous monitoring: Performance may change as input data evolves.
Real World Example
A national travel service is preparing for a public holiday sale where thousands of users may search, reserve, and pay for tickets at the same time.
A feature that works for one tester may fail under traffic, resource pressure, or infrastructure disruption. Ml functional performance helps the team focus on behavior under operational conditions.
The tester defines realistic traffic, failure, and recovery situations, then watches response time, errors, data consistency, and whether users can continue critical actions.
The release decision improves because Ml functional performance gives stakeholders evidence about service behavior when demand or disruption is no longer theoretical.
Practice Questions
Question 1
Which statement BEST describes Ml functional performance in the context of ISTQB terminology?
Question 2
A tester needs to explain Ml functional performance to a non‑technical stakeholder. Which approach is MOST appropriate?
Test your knowledge with real ISTQB-style questions
You’ve learned Ml Functional Performance. Test your understanding with topic-specific questions in our Mock Exams.