Data mining application: terrorism
Here is another example, certainly well known, of what data mining can do. Colleen McCue has written an interesting paper about this topic in the Defense Intelligence Journal. This article has the advantage to be understandable by people interested in data mining but not familiar with the topic of terrorism.
As written in the paper, the environment is saturated by information. The article shows why it is the case when dealing with terrorism data. Fayyad et al. (1) had already written that “The capacity of digital data storage worldwide has doubled every nine months for at least a decade, at twice the rate predicted by Moore’s Law for the growth of computing power during the same period“. It seems to be particularly true for terrorism data.
The paper covers areas such as information collection, identity theft and anomaly detection (among others) in a predictive analysis view. It is a comprehensive paper giving a good idea of nowadays applications in data mining against terrorism. When defining terrorism, the author writes “[…] terrorism can be described as violence with a larger agenda“. Although this definition is understandable, a more precise description of what exactly terrorism is would have been a plus.
If, like me, you want to know more about data mining and predictive analytics against terrorism, I suggest you the new book from McCue: Data Mining and Predictive Analysis: Intelligence Gathering and Crime Analysis.
(1) Usama M. Fayyad, Ramasamy Uthurusamy: Evolving data into mining solutions for insights. Commun. ACM 45(8): 28-31 (2002)