New answers tagged

0 votes

What clustering algorithms work best for datasets with only binary categorical features?

Any clustering algorithm should work -- the main issue is the similarity or distance metric that determines how similar (or different) two elements are. This is often something like Euclidean distance,...
user avatar
  • 5,002
2 votes
Accepted

What happens if all the features are correlated with each other before clustering?

Essentially, yes. One feature predicts to a reasonably high degree what the other features look like, so the additional features have limited discriminatory power. Obviously there is some effect, as ...
user avatar
  • 5,002
1 vote

How to handle list features in clustering?

You essentially want to have a numerical value to represent the similarity of the lists of two distinct objects. There are a number of metrics to deal with that, eg the Jaccard Index or Dice's ...
user avatar
  • 5,002

Top 50 recent answers are included