False Positive

noun

say it: “FAWLS POZ-ih-tiv” /ˈfɔls ˈpɑzətɪv/

A result that wrongly says 'yes': a test or model flags something that isn't really there.

What is a false positive?

A false positive is a false alarm: the model said yes, but the real answer is no, such as a normal payment flagged as fraud or a real email sent to junk. In scikit-learn's confusion matrix for two classes, it's the top-right count.

actual = [1, 0, 0, 1, 1, 0]    # 1 = fraud
guessed = [1, 0, 1, 0, 1, 0]
print(sum(a == 0 and g == 1 for a, g in zip(actual, guessed)))   # 1: a false alarm

In a sentence

  • “Every false positive meant a customer's card was frozen for nothing.”
  • “Raising the threshold cut the number of times a false positive froze a card.”

Level: Apprentice · More AI Basics terms at this level

Updated