S4E25 Cluster Analysis
Quantitude
The Hierarchical Agglomerative Algorithm
Hierarchical clustering is an algorithm that goes from n clusters all the way down to one cluster. The decision then is when do we stop? When are we smushing things across space that are really too far apart to be smushed? And there are a number of different guidelines just like when we do principal components analysis, we say how many components do we extract? Same thing in cluster analysis. But this is a hierarchical agglomerative strategy and historically it was very common, but it has a number of shortcomings," Jiffy says.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
