Affinity analysis

From Wikipedia, the free encyclopedia

Affinity analysis is a data analysis and data mining technique that discovers co-occurrence relationships among activities performed by (or recorded about) specific individuals, groups, or in general an object identifier in a computer science context.

An intuitive and well known example of affinity analysis is market basket analysis in the retail business. In this case retailers use it to understand the purchase behaviour of groups of customers, and use it for cross-selling, store design, discount plans and promotions. A widely used example of cross selling on the internet with market basket analysis is Amazon.com's use of suggestions of the type:

"Customers who bought book A also bought book B", e.g.

"People who read History of Portugal were also interested in Naval History".

In the case of retailers with stores, market basket information enables the retailer to understand the buyer's needs and rewrite the store's layout accordingly, develop cross-promotional programs, or even capture new buyers (much like the cross-selling concept). This even helps retailers avoid discounts, e.g. knowing that people who buy more than 12 cans of Pepsi also usually buy 12 cans of 7up during the same store trip, allows them not to discount both drinks at the same time, for the sale of one item usually leads to the sale of another.

However, affinity analysis can go well beyond the retail setting and has applications in other fields, e.g. in a medical database setting statements of the type "Patients who had procedure X later developed symptom Y" can be discovered with affinity analysis.