Chapter 13. Association Rules

In this chapter we describe the unsupervised learning methods of association rules (also called "affinity analysis"), where the goal is to identify item clusterings in transaction-type databases. Association rule discovery is popular in marketing, where it is called "market basket analysis" and is aimed at discovering which groups of products tend to be purchased together. We describe the two-stage process of rule generation and then assessment of rule strength to choose a subset. We describe the popular rule-generating Apriori algorithm and then criteria for judging the strength of rules. We also discuss issues related to the required data format and nonautomated methods for condensing the list of generated rules. The entire process is illustrated in a numerical example.


Put simply, association rules, or affinity analysis, constitute a study of "what goes with what." For example, a medical researcher wants to learn what symptoms go with what confirmed diagnoses. This method is also called market basket analysis because it originated with the study of customer transactions databases to determine dependencies between purchases of different items.

Discovering Association Rules in Transaction Databases

The availability of detailed information on customer transactions has led to the development of techniques that automatically look for associations between items that are stored in the database. An example is data collected using bar code scanners ...

Get Data Mining For Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel® with XLMiner®, Second Edition now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.