Boko Haram is one of the deadliest jihadist organisations on the planet. At its current rate, Boko Haram takes part in roughly one event every 10 hours, taking the lives of nearly 11 people daily. Yet, little is known concerning Boko Haram's internal structure or frequently travelled paths. Here, we apply a novel technique based on mobility patterns to analyse consecutive Boko Haram events to detect the mobility of the group [1]. Our work leverages a database of 3,800 events from the Armed Conflict Location & Event Data Project (ACLED) in which Boko Haram has been involved since the organisation became violent 10 years ago. Assuming that travel costs and reduced familiarity with unknown locations limit the mobility of Boko Haram members, we model the fragmentation of the group based on their footprint. We construct a spatial network based on the proximity of the terrorist events and detect edges which are frequently crossed by distinct group cells. Our results show that Boko Haram is a rather fragmented organisation in which at least 50-60 decentralised cells, capable of committing numerous and repetitive attacks against government and civilian targets. Our methodology also allows measuring the number of cross-border trips by Boko Haram, which is the number of times that our model predicts that a cell was active in two consecutive events located at a different side of a country border. Although the number of international border crossings varies according to the mobility of Boko Haram cells, our method shows that for a high and medium mobility scenario, roughly one-third of the journeys of a Boko Haram cell cross an international border, mostly between Nigeria and Cameroon or between Nigeria and Niger and that cross-border crossings have become more frequent.
