AI engineering glossary · Evaluation metrics
What is prediction interval coverage?
Prediction interval coverage (also called coverage probability, empirical coverage): The share of true values that actually fall inside the intervals a model predicts. A 90% interval is well calibrated if roughly 90% of outcomes land inside it. Coverage is checked alongside interval width, since very wide intervals cover well but are not useful.
Prediction interval coverage: an example
A demand forecaster issues 90% intervals for 100 weeks and only 78 actual values fall inside, so its coverage of 78% shows it is overconfident.
Related terms
More Evaluation metrics terms
- Prevalence
- Proper scoring rule
- R-precision
- Recall
- Recall at k
- Reciprocal rank
- Relevance judgments
- Reliability diagram
Where you learn it
Prediction interval coverage is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.