Feds Hunt Hummus and Pita Eaters

Posted by Ben Worthen

When used properly, data mining can help businesses better understand their customers. And then there are stories like this: The government searched through supermarket sales data to find people who bought Middle-Eastern food, thinking this would help spot terrorists.

The FBI obtained and mined sales data that San Francisco-area grocery stores collected in 2005 and 2006, according to CQ Politics. The agents were looking for a sudden spike in hummus sales that might indicate an Iranian sleeper cell in the Bay Area. An FBI higher-up killed the program, CQ Politics reports, on the grounds that it might be illegal and that it was, well, just ridiculous.

We’ve written about data mining in the past. It’s a way for companies to find patterns in the vast amounts of data they collect. The technique is a good for finding connections that you didn’t know exist. The most famous example – albeit one that may be an urban legend – is 7-11 learning that people who bought diapers also bought beer. The store supposedly discovered that its dads who buy diapers at a convenience store and many couldn’t resist picking themselves up a six pack. In response, 7-11 moved diapers and beer closer together.


Data mining works well when you’re comparing large samples or the cost of making a mistake is negligible. Needless to say, there’s no evidence that terrorists eat a disproportionate share of tabouli. And the cost of mistaking someone for a terrorist is a lot higher than having diapers too close to beer.

Flickr photo credit here.

Original article found here.