DBSCAN labels almost everything as noise. What do you change?
mediumAnswer
- The neighbourhood radius is too small for the density of your data, or the minimum points is too large.
- Set the minimum points from domain reasoning, often around twice the dimensionality, then choose the radius from the k-distance plot: sort every point's distance to its k-th nearest neighbour and pick the value at the knee, which is where density drops off.
- Check scaling first, since the radius is a single global distance and meaningless if features have different units.
- If clusters genuinely have very different densities, no single radius works and that is the algorithm's real limitation, so switch to HDBSCAN, which varies the density threshold and returns a hierarchy instead of forcing one global choice.
Check yourself — multiple choice
- Increase k
- The radius is too small or minimum points too large: scale features, read the radius from the k-distance knee, and move to HDBSCAN when cluster densities genuinely differ
- DBSCAN cannot be tuned
- Remove all outliers first
The k-distance knee sets the radius, and varying densities call for HDBSCAN.
#clustering#density
Practise Unsupervised Learning
214 interview questions in this topic.