The Calinski-Harabasz Index (CH Index) is another method for evaluating the quality of clustering

It is also known as the ‘Variance Ratio Criterion’, and it compares the dispersion between clusters with the dispersion within clusters. Higher values generally indicate better-defined clustering because the clusters are more distinct from each other.

$$ CH = \frac{\text{Tr}(B_k) \cdot (N - k)}{\text{Tr}(W_k) \cdot (k - 1)} $$

Where:

• $Tr(B_k$) is the trace of the between-cluster dispersion matrix,
• $Tr(W_k)$ is the trace of the within-cluster dispersion matrix,
• $N$ is the total number of points,
• $k$ is the number of clusters.

Next reading:

Dunn Index