How America built an AI tool to predict Taliban attacks
Subscribe to enjoy similar stories. In the summer of 2020 American intelligence analysts in Afghanistan got a warning from “Raven Sentry", an artificial-intelligence (AI) tool that they had been operating for a few months. There was a high probability, the AI told them, of a violent attack in Jalalabad, the capital of the eastern Nangarhar province, at the beginning of July.
It would probably cause between 20 and 40 casualties. The attack came, a little late, on August 2nd, when Islamic State struck the city’s prison, killing some 29 people. Raven Sentry had its origins in October 2019, when American forces in Afghanistan were facing a conundrum.
They had ever fewer resources, with troop numbers falling, bases closing and intelligence resources being diverted to other parts of the world. Yet violence was rising. The last quarter of 2019 saw the highest level of Taliban attacks in a decade.
To address the problem they turned to AI. Political violence is not random. A paper published in International Organisation by Andrew Shaver and Alexander Bollfrass in 2023 showed, for instance, that high temperatures were correlated with violence in both Afghanistan and Iraq.
When days went from 16°C highs to more than 38°C, they observed, “The predicted probability of an Iraqi male expressing support for violence against multinational forces [as measured in opinion polls] increased by tens of percentage points." Raven Sentry took this further. A team of American intelligence officers, affectionately dubbed the “nerd locker", was placed in a special forces unit, the culture of which is better suited to aggressive experimentation. They began by studying “recurring patterns" in insurgent attacks going back to the Soviet occupation of
. Read more on livemint.com
