Confusion Matrix
A table that counts true positives, true negatives, false positives and false negatives for a classification model, enabling detailed analysis of prediction performance across outcome categories.
In plain language
A four-square table showing exactly where your AI got it right and wrong. It shows how many times it correctly said yes, correctly said no, incorrectly said yes and incorrectly said no.
Why this matters
Confusion matrices are essential for AI governance because they reveal the true cost of errors. Different errors carry different business risks. Understanding your false positive and false negative rates helps you make informed decisions about deployment and risk acceptance.
Relevance
ImplementationThis metric directly supports model performance assessment and risk quantification, enabling your team to understand the real-world implications of AI accuracy.
Related terms
Putting confusion matrix into practice in your organisation?
Ready to transform your AI strategy?
Partner with Australia's AI strategy and governance specialists. From adoption roadmaps to ISO 42001 audit readiness.