What is inertia in K-Means and how is it interpreted?
Updated May 16, 2026
Short answer
Inertia is the total within-cluster sum of squared distances between points and their centroids.
Deep explanation
Lower inertia means tighter clusters. However, inertia always decreases as K increases, so it cannot be used alone to choose K.
Real-world example
Evaluating clustering compactness in segmentation systems.
Common mistakes
- Choosing K purely based on lowest inertia.
Follow-up questions
- Why does inertia decrease with K?
- What complements inertia?