40 Algorithms Every Programmer Should Know

Initialization

In order to group them, the k-means algorithm uses a distance measure to find the similarity or closeness between data points. Before using the k-means algorithm, the most appropriate distance measure needs to be selected. By default, the Euclidean distance measure will be used. Also, if the dataset has outliers, then a mechanism needs to be devised to determine the criteria that are to be identified and remove the outliers of the dataset.