Back to metrics

NMI

C Clustering

Normalized Mutual Information

Direction

Higher is Better

Value Range

[0, 1]

Category

Clustering

Agreement with reference labels

Description

Measures the mutual information between predicted clusters and true labels, normalized by the entropy of the two distributions

Mathematical Formula

NMI(Y, Ŷ) = I(Y; Ŷ) / √(H(Y) * H(Ŷ))

Interpretation Guide

Range [0, 1]. 1 = perfect clustering match with ground truth. Symmetric, accounts for chance clustering.

Related Metrics

Other metrics in the Clustering category

ARI

↑

Similarity between predicted and true clusters adjusted for chance

ASW

↑

Average silhouette coefficient measuring cluster cohesion and separation

DAV

↓

Average similarity between each cluster and its most similar neighboring cluster