How can we measure the goodness of the clusters in the Hierarchical Clustering Algorithm?

There are many measures to find the goodness of clusters but the most popular one is the Dunn’s Index.

Dunn’s index is defined as the ratio of the minimum inter-cluster distances to the maximum intra-cluster diameter and the diameter of a cluster is calculated as the distance between its two furthermost points i.e, maximum distance from each other.


  • In order to have well separated and compact clusters, we should aim for a higher value of Dunn’s index.

Assessment Metrics for Clustering Algorithms

Image Source: Google Images