Comments on: Data mining for terrorism: is it working? http://www.dataminingblog.com/data-mining-for-terrorism-is-it-working/ Data mining crossroads - research, applications, news, list of blogs and customized search engine about data mining. Tue, 07 Feb 2012 08:14:55 +0100 http://wordpress.org/?v=2.8.5 hourly 1 By: Sandro Saitta http://www.dataminingblog.com/data-mining-for-terrorism-is-it-working/comment-page-1/#comment-480 Sandro Saitta Thu, 22 Feb 2007 16:35:00 +0000 http://www.dataminingblog.com/data-mining-for-terrorism-is-it-working#comment-480 It is very interesting to see how the topic of data mining against terrorism is subject to discussion. Today, I write about Jonas' paper which shows the other side of the coin... It is very interesting to see how the topic of data mining against terrorism is subject to discussion. Today, I write about Jonas’ paper which shows the other side of the coin…

]]> By: Dean Abbott http://www.dataminingblog.com/data-mining-for-terrorism-is-it-working/comment-page-1/#comment-479 Dean Abbott Wed, 21 Feb 2007 22:18:00 +0000 http://www.dataminingblog.com/data-mining-for-terrorism-is-it-working#comment-479 Very interesting post. I found the quote "Using sophisticated computerized screening programs" to be the crux of the argument. In other words, it is the automation of screening millions of transactions in ways human analysts cannot do that is the real innovation. Of course the question is this: is there sufficient information to identify with any reasonably high confidence that a event or pattern is linked to a terrorist group. <br/><br/>I personally believe this should be tried, but also believe it is a very tough row to hoe.<br/><br/>Thanks for alerting us to the article! Very interesting post. I found the quote “Using sophisticated computerized screening programs” to be the crux of the argument. In other words, it is the automation of screening millions of transactions in ways human analysts cannot do that is the real innovation. Of course the question is this: is there sufficient information to identify with any reasonably high confidence that a event or pattern is linked to a terrorist group.

I personally believe this should be tried, but also believe it is a very tough row to hoe.

Thanks for alerting us to the article!

]]>