Ml Model
An ML model is a mathematical representation learned from training data that makes predictions, classifications, or decisions for new input data.
“An implementation of machine learning that generates a prediction, classification or recommendation based on input data.”
(Definition reproduced from the ISTQB Glossary. Copyright belongs to ISTQB.)
View the complete ISTQB GlossaryWhat is Ml Model?
The model identifies patterns from historical data and applies them to unseen data during inference.
Training: The model learns relationships from labeled or unlabeled data.
Inference: Trained models generate predictions for new inputs.
Continuous improvement: Models may require retraining as data changes.
Real World Example
A regulated product team is preparing a release where Ml model appears in reviews, test design conversations, or defect triage rather than as an isolated glossary word.
The risk is that the team treats Ml model as interchangeable with nearby ISTQB terms. That makes test scope blurry and can lead to weak evidence for the release decision.
The tester anchors the discussion in the official definition, asks where the concept appears in the product, and designs examples that show the difference between Ml model and similar ideas.
The page becomes useful in practice because Ml model is connected to a specific testing decision, not memorized as a detached definition.
Practice Questions
Question 1
Which statement BEST describes Ml model in the context of ISTQB terminology?
Question 2
A tester needs to explain Ml model to a non‑technical stakeholder. Which approach is MOST appropriate?
Test your knowledge with real ISTQB-style questions
You’ve learned Ml Model. Test your understanding with topic-specific questions in our Mock Exams.