Chapter 9. Mining for Data Anomalies

In the previous eight chapters, we have used data mining techniques to identify a wide variety of patterns in data. We have mined social networks, associations, matching pairs, and all sorts of interesting text patterns. Now we are going to turn the tables and use our skills to look for anomalies, or data items that do not match an expected pattern. Data anomalies happen for various reasons, but because they deviate from expectations or stand out in some important way, we can use our data mining knowledge to seek them out. In my toolbox of mining techniques, I like to think of data mining for anomalies as using the claw part of a hammer. Most of the time I am using a hammer to pound nails, but every once in ...

Get Mastering Data Mining with Python – Find patterns hidden in your data now with the O’Reilly learning platform.

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