Finding clusters of similar cases

With cluster analysis, you try to find specific groups of cases, based on the similarity of the input variables. These groups, or clusters, help you understand your cases, for example, your customers or your employees. The clustering process groups the data based on the values of the variables, so the cases within a cluster have high similarity; however, these cases are very dissimilar to cases in other clusters. Similarity can be measured with different measures. Geometric distance is an example of a measure for similarity. You define an n-dimensional hyperspace, where each input variable defines one dimension, or one axis. Values of the variables define points in this hyperspace; these points are, of course, the cases. Now you can measure the geometric distance of each case from all other cases.

There are many different clustering algorithms. The most popular one is the K-means algorithm. With this algorithm, you define the number of K clusters in advance...