Clustering is an unsupervised machine learning approach to partition a dataset into a set of groups or clusters, but sometimes it has a tendency to form clusters even though the data does not contain any clusters. Hence, it's essential to validate the quality of the clustering output. Broadly, clustering validation statistics can be categorized into four classes:
- Relative clustering validation: It evaluates the clustering structure by varying different parameter values for the same algorithm (namely, varying the number of clusters k).
- Internal clustering validation: It uses internal information such as (silhouette width, Dunn index) of the clustering process to evaluate the goodness of a clustering structure.
- External cluster validation: It uses ground truth information from the user about how the data should be grouped. As we know the true...