SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-threshold-precision-recall-tradeoff

Raising a classifier's threshold usually does what to false positives and false negatives?

Fewer false positives, more false negatives.

Start playing free

  1. Fewer false positives, more false negatives ✔
  2. More false positives, fewer false negatives
  3. Both go down together

Why: A higher threshold means the model says positive only when very sure. It makes fewer wrong positive calls but misses more real positives. So precision tends to rise while recall falls.

Huh, didn't know that: Because of this, precision and recall often move in opposite directions.

The dad joke
I raised my threshold for dad jokes. Now I miss a lot of good ones, but none of the bad ones get through.
Like this card?
Play the game

References

Answer: Fewer false positives, more false negatives. A higher threshold means the model says positive only when very sure. It makes fewer wrong positive calls but misses more real positives. So precision tends to rise while recall falls.

  1. Google ML Crash Course: Accuracy, recall, precision developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall
    increasing the classification threshold tends to decrease the number of false positives and increase the number of 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 IntelligenceHow do AI, machine learning and deep learning fit together?Artificial IntelligenceWhat did Alan Turing call his 1950 test of machine intelligence?Artificial IntelligenceTuring predicted that by about 2000, judges would ID the machine at most what percent of the time?

That's stuff everyone should know.