K-Means is one of the most popular unsupervised machine learning techniques that is used to create clusters, and so categorizes data.
An intuitive example could be posed as follows:
Say a university was offering a new course on American History and Asian History. The university maintains a 15:1 student-teacher ratio, so there is 1 teacher per 15 students. It has conducted a survey which contains a 10-point numeric score that was assigned by each student to their preference of studying American History or Asian History.
We can use the in-built K-Means algorithm in R to create 2 clusters and presumably, by the number of points in each cluster, it may be possible to get an estimate of the number of students ...