This chapter is about unsupervised machine learning algorithms. The chapter starts with an introduction to unsupervised learning techniques. Then, we will learn about two clustering algorithms: k-means clustering and hierarchical clustering algorithms. The next section looks at a dimensionality reduction algorithm, which may be effective when we have a large number of input variables. The following section shows how unsupervised learning can be used for anomaly detection. Finally, we will look at one of the most powerful unsupervised learning techniques, association rules mining. This section also explains how patterns discovered from association rules mining represent interesting relationships between the various data elements across transactions that can help us in our data-driven decision making.  

By the end of this chapter, the reader should be able to understand how unsupervised learning can be used to solve some real-world problems. The reader will understand the basic algorithms and methodologies that are currently being used for unsupervised learning.

In this chapter, we will cover the following topics:

• Unsupervised learning
• Clustering algorithms
• Dimensionality reduction 
• Anomaly detection algorithms
• Association rules mining