Clustering & Unsupervised Learning

Clustering is the art of finding structure in the unlabelled.

Introduction

Clustering discovers natural groupings in data without predefined labels. It is widely used for customer segmentation, anomaly detection, and exploratory analysis.

What You Will Learn

• Implement partition-based, hierarchical, and density-based clustering
• Evaluate cluster quality using internal and external metrics
• Visualise and interpret cluster results
• Apply clustering to real workplace scenarios

Assessment Connection

Section A — you must justify your algorithm choice and the number of clusters selected.

Content

TutorialsHow-to GuidesReferenceExplanation

• k-Means Clustering
• Hierarchical Clustering
• DBSCAN & Density-Based Methods
• Evaluating Cluster Quality

• Find the Optimal Number of Clusters
• Cluster Mixed Data Types
• Build a Customer Segmentation

• Clustering Algorithms Comparison
• Cluster Evaluation Metrics

• When Clustering Fails
• Clustering vs Classification