The objectives of this section are:
to introduce you to the concept of association analysis
to explain the basic problem that association rules present
to excite you to delve deeper into the world of data mining
By the time you have completed this section you will be able to:
describe what association analysis is
define the key terms described in the problem definition
If I were to walk up to you with a tape measure, measure your waist and then tell you that based on your waist size that you were going to have cancer in 10 years would you pay me any mind?
What if I were to walk up to you and tell you that out of the next five people who walked out of the local supermarket 3 of them would be carrying a case of beer and a box of diapers would you take me seriously?
Now what if I were to present you with a computational model that could find the items that are frequently bought together by customers, would you then be more inclined to believe what I have to say?
This is what association analysis is all about. Association Analysis is a key area of data mining which focuses on discovering interesting and useful hidden relationships in large data sets.
Have you ever been browsing on the internet and saw an ANNOYING flashing ad that caught your attention because you were interested in the product? Have you ever stopped to wonder how they knew you would like to buy that item? This is Association Analysis at work. By tracking the sites you visit, they can compile a list of similar products that you might purchase. Association analysis usefulness is not limited to the sales industry its applications extend to other fields such as: