Micro Averaging#
Aggregating counts across classes before computing a metric.
Important
✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.
What it is#
Micro averaging aggregates a metric by pooling the counts — it sums the true positives, false positives and false negatives across all classes first, then computes precision, recall or F1 from those totals. Every instance counts equally, so frequent classes dominate.
Its behavior#
Because it is driven by raw counts, micro averaging gives an overall, accuracy-flavored number — in fact, for single-label multiclass, micro-F1 equals accuracy. Its weakness is that strong performance on a big class can mask poor performance on a small one.
When to use it#
Reach for micro averaging on balanced problems, in multilabel settings, or whenever you want a single global score reflecting overall correctness. Pair it with macro to expose whether minority classes are being hidden.
Theme: Classification & Averaging Metrics · All terminology
Hint
Mind map — connected ideas
Macro Averaging · Weighted Averaging · Micro AUC · One-vs-Rest (OvR) · Precision (a.k.a. Positive Predictive Value, PPV) · Multiclass Classification
Hint
More in Classification & Averaging Metrics
Accuracy · AUC (Area Under the Curve) · Average Precision (AP) · Binary Classification · Classification Probability · Discriminatory Power · F1-score · Gini Coefficient · Harmonic Mean · Log Loss (also called Logarithmic Loss or Cross-Entropy Loss) · Macro AUC · Macro AUROC (Macro-Averaged AUROC) · Macro Averaging · Macro F1
See also
Source article Adapted (context, re-expressed) in our own words from: Micro Averaging (insightful-data-lab.com).