For single-label multiclass prediction over all classes, why do micro precision, recall and F1 equal accuracy?
Classic MLLevel: AdvancedMicro scores in multiclass
For single-label multiclass prediction over all classes, why do micro precision, recall and F1 equal accuracy?
Hints
- Count what one misclassified row contributes.
- This identity depends on including every class.
Answer
This answer is part of mentoring
Advanced questions come with a full breakdown and a mock interview with a working quant researcher. The first call is free.
Source and licence: scikit-learn 1.7.2 — model evaluation · BSD-3-Clause · answer: Quantoros editorial