Introduction

Clustering algorithms, which are central to cluster analysis, help identify natural groupings within our data. They analyse patterns and similarities between data points to organise them into meaningful clusters.

The core principle behind clustering is to maximise similarity within groups while maximising differences between groups. This allows for the discovery of inherent structures in data without pre-existing labels.

There are a number of different algorithms that are commonly used for cluster analysis, including:

• K-means clustering
• Hierarchical clustering
• DBSCAN
• Gaussian Mixture models

Content map

To learn more about clustering algorithms, read each of the following sections:

K-means Clustering

Hierarchical Clustering

DBSCAN

Gaussian Mixture Models

Next element

Validating clusters