Hadoop MapReduce v2 Cookbook - Second Edition

Chapter 9. Classifications, Recommendations, and Finding Relationships

In this chapter, we will cover:

• Performing content-based recommendations
• Classification using the naïve Bayes classifier
• Assigning advertisements to keywords using the Adwords balance algorithm

Introduction

This chapter discusses how we can use Hadoop for more complex use cases like classifying a dataset and making recommendations.

The following are a few instances of some such scenarios:

• Making product recommendations to users either based on similarities between products (for example, if a user liked a book about history, he/she might like another book on the same subject) or on user behavior patterns (for example, if two users are similar, they might like books the other has read) ...