SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-recall-catches-positives

Which metric answers: of all the real positives, how many did the model catch?

Recall, also called the true positive rate.

Start playing free

  1. Precision
  2. Accuracy
  3. Recall ✔

Why: Recall is true positives divided by true positives plus false negatives. A cancer screen with high recall misses very few real cases.

Huh, didn't know that: When actual positives exist, labeling every example positive gives recall 1.0, even if precision is poor.

The dad joke
My memory has terrible recall. I can never find all the positives in my day.
Like this card?
Play the game

References

Answer: Recall. Recall is true positives divided by true positives plus false negatives. A cancer screen with high recall misses very few real cases.

  1. Google ML Crash Course: Accuracy, recall, precision developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall
    the proportion of all actual positives that were classified correctly as positives
    Checked 2026-10-10.
  2. Google Machine Learning Glossary: recall developers.google.com/machine-learning/glossary
    180 were true positives. 20 were false negatives.
    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 IntelligenceIf 1 percent of cases are positive, what accuracy does always guessing negative score?Artificial IntelligenceHow do AI, machine learning and deep learning fit together?Artificial IntelligenceWhat did Alan Turing call his 1950 test of machine intelligence?

That's stuff everyone should know.