DATA MINING
Desktop Survival Guide by Graham Williams |
|||||
Health data is another example where association analysis can be effectively employed. Suppose a patient is obtaining a series of pathology and diagnostic imaging tests as part of an investigation to determine the cause of some symptoms. The ``shopping basket'' here is the collection of tests performed. Are there items in the basket that don't belong together? Or are there some patients who don't seem to be getting the appropriate selection of tests? The Australian Health Insurance Commission discovered an unexpected correlation between two pathology tests performed by pathology laboratories and paid for by insurance viveros.nearhos.etal:99:hic.assoc. It turned out that only one of the tests was actually necessary, yet regularly both were being performed. The insurance organisation was able to reduce over-payment by disallowing payment for both tests, resulting in a saving of some half a million dollars per year.
In a very different application, IBM's Advance Scout was developed to identify different strategies employed by basketball players in the US NBA. Discoveries include the observation that Scottie Pippen's favorite move on the left block is a right-handed hook to the middle. And when guard Ron Harper penetrates the lane, he shoots the ball 83% of the time. Also it was noticed that 17% of Michael Jordan's offence comes on isolation plays, during which he tends to take two or three dribbles before pulling up for a jumper bhandari.colet.etal:1997:advan_scout.
There are many more examples of unexpected associations having been discovered between items and, importantly, found to be particularly useful for improving business (and other) processes.
Copyright © 2004-2006 [email protected] Support further development through the purchase of the PDF version of the book.