So far in this book we have explored a variety of descriptive and diagnostic statistical methods that can easily be applied to out-of-memory data sources. But the true potential of modern data science resides in its predictive and prescriptive abilities. In order to harness them, versatile data scientists should understand the logic and implementations of techniques and methods commonly known as machine learning algorithms, that allow making robust predictions and foreseeing patterns of events. In this chapter we will introduce you to machine learning methods that are applicable to Big Data classification and clustering problems through the syntax of the R language. Moreover, the contents of this chapter will provide you with the following skills:
You will understand the concept of machine learning and be able to distinguish between supervised/unsupervised methods and clustering/classification models
You will carry out a high...