Please enable JavaScript.
Coggle requires JavaScript to display documents.
Clustering - Coggle Diagram
Clustering
What is it?
Grouping of observations on the basis of their features
Organizing data points into "homogenous" and meaningful groups = clusters
A form of unsupervised learning/Exploratory/No clear outcome
NOT pre-defined, discovered from data
Applications
Discover natural groups & patterns in the data
Facilitate the analysis of very large datasets
Input
A dataset of N columns/features & M rows/records
This dataset had M observations of N dimensions
Output
Cluster
Organizing data into most natural groups
Evaluate outputs
High intra-similarity
data points in the same cluster should be similar to each other
Low inter-similarity
data points in different clusters should be different "enough" from each other