Fig. 2: Distortion score plot for determining optimal number of clusters.

The plot displays the distortion scores (within-cluster sum of squares) for K-means clustering, with the number of clusters (K) ranging from 1 to 10. The “elbow point,” indicating the optimal number of clusters, is observed at K = 4, where the rate of decrease in distortion significantly slows down. This suggests that 4 clusters provide a suitable balance between model simplicity and accuracy for this dataset.