Confusion Matrix
A confusion matrix is a table that summarises a classifier's results by counting correct and incorrect predictions for each class.
What is Confusion Matrix?
For a two-class problem it shows true positives, false positives, true negatives and false negatives. It reveals which errors a model makes, which a single accuracy figure hides, and is useful for checking performance across demographic groups.
How it works
Rows typically show the actual class and columns the predicted class; the diagonal holds correct predictions.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions