Can data science help fight terrorism? This China-based research team thinks it can
- Scientists led by a team at Zhejiang University in eastern China said they could help provide ‘interpretable and accurate predictions of terrorism’
- No one can predict ‘black swan’ incidents, said team leader Andre Python, but analysis can help identify the most likely times and locations
A research team led by a China-based researcher has said machine learning algorithms can provide a predictive tool that will help fight terrorism.
The team, led by Andre Python from the data science centre at the Zheijiang University in Hangzhou, said their models can “produce interpretable and accurate predictions of terrorism ... particularly in areas already experiencing relatively high levels of terrorism activity”.
“Several thousand people die every year worldwide because of terrorist attacks perpetrated by non-state actors,” the team, which also featured six researchers from four institutes in Britain and Germany, wrote in the study, published in the journal Science Advances on Friday
However, Python also acknowledged in a press release from the university that “it is virtually impossible to predict black swan events”, which happen only once over a very long time.
“This means that to prevent a large proportion of terrorist events in a region that is not much affected by terrorism, important resources are required to survey large areas where terrorism can potentially occur,” he said.
Python’s team defined terrorism as politically motivated attacks outside legitimate warfare that are perpetrated by non-state actors to communicate to a wider audience.