Precision Calculator

Precision answers "of all the times the model predicted positive, how often was it right?" It is TP ÷ (TP + FP), and it matters when false alarms are expensive — spam filters, fraud detection, medical screens. Enter your confusion-matrix counts to get precision and the false discovery rate.

Correctly predicted positives.

Predicted positive but actually negative.

Predicted negative but actually positive.

Correctly predicted negatives.

Result

Enter your values and press Calculate — the result appears here.

Worked examples

50 correct out of 60 positive predictions

  • tp = 50
  • fp = 10
  • fn = 5
  • tn = 35

Result: Precision 0.8333 · False discovery rate 0.1667

No false alarms

  • tp = 30
  • fp = 0
  • fn = 10
  • tn = 60

Result: Precision 1.00

Frequently asked questions

What does precision tell me?

Precision is the reliability of a positive prediction: of everything the model flagged as positive, the fraction that was genuinely positive. High precision means few false alarms.

When is precision the right metric?

When a false positive is expensive: spam that blocks a real email, fraud alerts that freeze a legitimate card, or medical screenings that cause unnecessary anxiety. There you optimize precision, even at the cost of recall.

What is the false discovery rate?

The complement of precision (1 − precision): the share of positive predictions that were actually wrong. Precision 0.8333 means 16.67% of positive predictions were false alarms.

💬 Discuss on BestWordz Community

Join the conversation about Machine Learning, precision, precision calculator on the BestWordz Community forum.

Visit Forum →
Copied!