EasyDeepLearn

Interview: 'discuss the tradeoffs between k-means, DBSCAN, and HDBSCAN.'

medium

Answer

  • (1) k-means: fast, scales to millions (mini-batch), but assumes spherical + equal-size clusters + fixed k + non-robust to outliers.
  • (2) DBSCAN: handles non-convex + detects noise, but needs eps tuning + fails with varying densities + O(n log n) with index.
  • (3) HDBSCAN: no eps tuning + handles varying densities + hierarchy + stability, but slower + memory-heavy for big data + hyperparameter minclustersize\operatorname{min}_{\mathrm{cluster}}\mathrm{size} still matters.
  • Rule: k-means → baseline / large-scale; DBSCAN → known density; HDBSCAN → real-world exploration.
Check yourself — multiple choice
  • Same
  • k-means (fast, big scale, spherical only) vs DBSCAN (non-convex + noise, but eps sensitive + fails varying density) vs HDBSCAN (no eps + varying density + hierarchy + stability, slower)
  • Random
  • Only one

k-means fast+spherical; DBSCAN non-convex+noise; HDBSCAN varying density+hierarchy.

#interview#clustering

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions