Mahout was introduced in Chapter 2, Java Libraries and Platforms for Machine Learning, as a scalable machine learning library. It provides a rich set of components with which you can construct a customized recommendation system from a selection of algorithms. The creators of Mahout say that it is designed to be enterprise-ready; it's designed for performance, scalability, and flexibility.

Mahout can be configured to run in two flavors: with or without Hadoop, and for a single machine and distributed processing, respectively. We will focus on configuring Mahout without Hadoop. For more advanced configurations and further uses of Mahout, I would recommend two recent books: Learning Apache Mahout, by Chandramani Tiwary, Packt Publishing, and Learning Apache Mahout Classification, by Ashish Gupta, Packt Publishing.

As Apache Mahout's build and release system is based on Maven, you will need to learn how to install it. We will look at the most convenient approach; using Eclipse with the Maven plugin.