K-Means Clustering

An unsupervised learning algorithm for finding patterns in data.

How it works

1. Initialization

Pick K random points as starting centroids.

2. Assignment

Assign every data point to its nearest centroid.

3. Update

Move each centroid to the average position of its points.

Repeat steps 2 and 3 until the centroids stop moving.

Configuration

Number of Clusters (K) 3

Show Distance Lines

Visualize error components of WCSS

Elbow Method (WCSS)

Ready Iter: 0 WCSS: -

Click on canvas to add points

Did you know? K-Means is a "greedy" algorithm. It finds a local optimum based on its starting points. Try resetting several times with the same data to see how different initial starting points lead to different results!