SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-confusion-matrix

What does a confusion matrix show for a classifier?

Counts of correct and incorrect predictions, by actual and predicted class.

Start playing free

  1. How long each prediction took
  2. The model's weights after training
  3. Counts of right and wrong predictions per class ✔

Why: A confusion matrix is an N by N table for N classes. For yes/no tasks its four cells are true positives, false positives, true negatives and false negatives.

Huh, didn't know that: Precision, recall and accuracy can all be computed from those four cells.

The dad joke
I made a confusion matrix of my weekend plans. Mostly false positives.
Like this card?
Play the game

References

Answer: Counts of right and wrong predictions per class. A confusion matrix is an N by N table for N classes. For yes/no tasks its four cells are true positives, false positives, true negatives and false negatives.

  1. Google Machine Learning Glossary: confusion matrix developers.google.com/machine-learning/glossary
    An NxN table that summarizes the number of correct and incorrect predictions that a classification model made.
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceWhat makes a regression model different from a classification model?Artificial IntelligenceTuring predicted that by about 2000, judges would ID the machine at most what percent of the time?Artificial IntelligenceIn machine learning, what is inference?

That's stuff everyone should know.