EasyDeepLearn

Davies-Bouldin index — how is it computed?

hard

Answer

  • DB = (1/k) Σi{\Sigma}_{i} max⁡j≠i\operatorname{max}_{j \ne i} [(si  +  sj)  /  dij][(s_{i}\; + \;s_{j})\; / \;d_{\mathrm{ij}}] where si  =  within−clusters_{i}\; = \;\mathrm{within} - \mathrm{cluster} scatter, dij  =  distanced_{\mathrm{ij}}\; = \;\mathrm{distance} between centroids.
  • Lower is better.
  • Rewards compact + well-separated clusters.
  • Fast, ground-truth-free.
  • Weak on non-convex clusters (assumes centroid representation).
  • Standard internal metric alongside silhouette.
Check yourself — multiple choice
  • Higher is better
  • Lower is better; (1/k) Σ max⁡j\operatorname{max}_{j} (si  +  sj)/dij(s_{i}\; + \;s_{j}) / d_{\mathrm{ij}} → compact + separated clusters; weak on non-convex
  • Same as CH
  • Random

Davies-Bouldin: lower = better; combines scatter + centroid distance.

#clustering#evaluation

Practise Unsupervised Learning

214 interview questions in this topic.

Read the lessonFlashcardsTake the quiz

Related questions