AI engineering glossary · Evaluation metrics
What is micro averaging?
Micro averaging (also called micro-average, micro F1): A way to combine per-class results in multiclass problems by pooling the true positives, false positives and false negatives from all classes first and then computing one metric. Large classes dominate the result. For single-label multiclass tasks, micro-averaged precision, recall and F1 all equal accuracy.
Micro averaging: an example
Pooling counts over 3 classes with 900 correct out of 1,000 predictions gives micro precision, recall and F1 all equal to 0.90.
Related terms
More Evaluation metrics terms
- Negative predictive value
- Normalised discounted cumulative gain
- Normalised mutual information
- Normalised RMSE
- Operating point
- Partial AUC
- pass@k
- Perplexity
Where you learn it
Micro averaging is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.