K-means clustering is one of the most widely used unsupervised machine learning techniques and is used mainly for data mining purposes. K-means is not particularly; exclusive to location data but is also used in diverse applications to partition observations into clusters (k). In a classic k-means clustering, the full weights are on attribute similarity, while location-based k-means specifically targets geographic coordinates to derive spatial or location similarity. We will use the latter as we are interested in location data analysis.
The k-means algorithm is based on randomly selecting k (where k is the number of clusters specified) number of objects that represent initially a cluster mean or center. Then, the algorithm assigns other objects to the cluster, which is closely based on the Euclidean distance between the object and cluster mean. The k-means...
