How does K-means clustering work? (opens in new tab)

K-means clustering (not to be confused with K-nearest neighbors) is an unsupervised learning algorithm used for grouping similar points together into clusters. start Algorithm The basic K-means algorithm is fairly simple and has two steps, repeated until convergence: assign points to cluster corresponding to closest centroid update centroid locations to the mean of all points assigned to the associated cluster The algorithm converges when the centroids stop moving, i.e. no points can be switc...