Clustering is a technique used to group similar objects (close in terms of distance) together in the same group (cluster). Unlike supervised learning methods (for example, classification and regression) covered in the previous chapters, a clustering analysis does not use any label information, but simply uses the similarity between data features to group them into clusters.

Clustering can be widely adapted in the analysis of businesses. For example, a marketing department can use clustering to segment customers by personal attributes. As a result of this, different marketing campaigns targeting various types of customers can be designed.

The four most common types of clustering methods are hierarchical clustering, k-means clustering, model-based clustering, and density-based clustering:

• Hierarchical clustering: This creates a hierarchy of clusters, and presents the hierarchy in a dendrogram. This method does not require the number of clusters to be specified at the beginning.
• k-means clustering: This is also referred to as flat clustering. Unlike hierarchical clustering, it does not create a hierarchy of clusters, and it requires the number of clusters as an input. However, its performance is faster than hierarchical clustering.
• Model-based clustering: Both hierarchical clustering and k-means clustering use a heuristic approach to construct clusters, and do not rely on a formal model. Model-based clustering assumes a data model and applies an EM algorithm to find the most likely model components and the number of clusters.
• Density-based clustering: This constructs clusters in relation to the density measurement. Clusters in this method have a higher density than the remainder of the dataset.

In the following recipes, we will discuss how to use these four clustering techniques to cluster data. We will discuss how to validate clusters internally, using within clusters the sum of squares, average silhouette width, and externally, with ground truth.