Practical Data Analysis Cookbook

Chapter 4. Clustering Techniques

In this chapter, we will cover various techniques that will allow you to cluster the outbound call data of a bank that we used in the previous chapter. You will learn the following recipes:

• Assessing the performance of a clustering method
• Clustering data with the k-means algorithm
• Finding an optimal number of clusters for k-means
• Discovering clusters with the mean shift clustering model
• Building fuzzy clustering model with c-means
• Using a hierarchical model to cluster your data
• Finding groups of potential subscribers with DBSCAN and BIRCH algorithms

Introduction

Unlike a classification problem, where we know a class for each observation (often referred to as supervised training or training with a teacher), clustering models ...