Study Finds Way To Predict Terrorist Activities — With 90% Accuracy
BINGHAMTON, N.Y. — “Predictive policing” technology has been utilized by law enforcement across the country in recent years as a means to stop crime before it happens, but could “predictive anti-terrorism” be next?
Researchers at Binghamton University in New York have developed a framework that claims to predict future terrorist activities by pinpointing similar patterns in previous attacks.
“Predicting terrorist events is a dream, but protecting some area by using patterns is a reality. If you know the patterns, you can reduce the risks. It’s not about predicting, it’s about understanding,” says Salih Tutun, a PhD student at Binghamton who developed the technology, in a university news release.
Tutun’s proposed design — called the Networked Pattern Recognition (NEPAR) Framework — works by defining useful patterns of past attacks to understand behaviors and analyze and detect potential terrorist behaviors in the future.
Using data from over 150,000 terrorist attacks between 1970 and 2015, the framework calculates the relationships among terrorist attacks — such as weapon time and attack time among other factors — to detect behaviors within the scope of these connections with over 90 percent accuracy. In fact, the research purports to identify the extension of attacks with 90 percent accuracy, multiple attacks with 96 percent accuracy, and terrorist goals with 92 percent accuracy.
According to Tutun, the results of the study, which were published in the journal Expert Systems with Applications, could help governments better control terrorism and even allow law enforcement to come up with reactive countermeasures.
“When you solve the problem in Baghdad, you solve the problem in Iraq. When you solve the problem in Iraq, you solve the problem in the Middle East. When you solve the problem in the Middle East, you solve the problem in the world,” said Tutun. “Because when we look at Iraq, these patterns are happening in the USA, too.”
Previous studies on terrorist behavior focused on individuals rather than analyzing the dynamic interactions and patterns within terrorist networks, according to the release.