Data Science and Statistics

Precision, explained

Precision measures how many predicted positives are actually positive.
Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

Precision measures how many predicted positives are actually positive.

Intuition

Precision asks: when the model says yes, how often is it right?

Technical Definition

Precision is true positives divided by true positives plus false positives.

Example

In spam detection, precision measures how often emails flagged as spam really are spam.

Common Misunderstandings

Precision does not measure how many real positives were found.
Optimizing precision alone can miss many valid positives.

Same Category

More from Data Science and Statistics

AccuracyAccuracy is the fraction of predictions a model gets correct.AUC ROCAUC ROC summarizes how well a classifier ranks positive examples above negative examples across thresholds.CalibrationCalibration measures whether predicted probabilities match observed frequencies.CausationCausation means that changing one variable would produce a change in another variable under the right conditions.Confidence IntervalA confidence interval is a range that estimates an unknown quantity with uncertainty from sampling.Confusion MatrixA confusion matrix counts correct and incorrect classification outcomes by predicted and actual class.

Related Reading

Essays that use this concept

Data Science and EvaluationPrecision vs Recall vs F1 Score

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.

Browse Glossary