Glossary · Phase 3 · Machine learning
Inertia
How tight a k-means clustering is: the total squared distance from each point to its cluster's center. Lower is tighter.
To track progress, k-means uses one number, the inertia. For each point, take its distance to its own center and square it. Then add up all those squares. A small inertia means points sit close to their centers, so the clusters are tight.
Try it now
Press Next step to alternate the two moves from this section. New start shows that the first guess matters.
Learn it properly
Clustering · Group similar items without labels (k-means). About 35 minutes.
Other terms from the same lesson
- clustering: Grouping similar examples together without being told the groups in advance.
- elbow method: Picking the number of clusters where adding more stops making the clusters much tighter: the bend in the curve.
- silhouette score: How well each point sits in its own cluster rather than the next one: near 1 is clear-cut, near 0 is on a border.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.