A generative model for predicting terrorist incidents

Abstract

A major concern in coalition peace-support operations is the incidence of terrorist activity. In this paper, we propose a generative model for the occurrence of the terrorist incidents, and illustrate that an increase in diversity, as measured by the number of different social groups to which that an individual belongs, is inversely correlated with the likelihood of a terrorist incident in the society. A generative model is one that can predict the likelihood of events in new contexts, as opposed to statistical models which are used to predict the future incidents based on the history of the incidents in an existing context. Generative models can be useful in planning for persistent Information Surveillance and Reconnaissance (ISR) since they allow an estimation of regions in the theater of operation where terrorist incidents may arise, and thus can be used to better allocate the assignment and deployment of ISR assets. In this paper, we present a taxonomy of terrorist incidents, identify factors related to occurrence of terrorist incidents, and provide a mathematical analysis calculating the likelihood of occurrence of terrorist incidents in three common real-life scenarios arising in peacekeeping operations.

Parameterising the dynamics of inter-group conflict from real world data

“…This can be used to estimate the typical probabilities of actions being performed for groups with given characteristics (e.g., as defined in Section V-A). This can also include fitting to appropriate statistical distributions, which may feature as an important component in particular types of generative models (e.g., [1]). This is shown in Figure 4 where we apply Beta distribution fittings as an example, by computing the maximum likelihood estimates of the beta distribution parameters [24].…”

“…A major concern in asymmetric warfare is the threat faced by coalition operations, originating from insurgent group activity [1], [2]. In many cases such groups are loosely and chaotically organised, but their ideals are sociologically and psychologically embedded across members such that the group has expected behaviours that can represent a major threat.…”

“…Frequently embodied through agent-based computation [7], this involves a model of human behaviour, often with a stochastic component (e.g., [1]), that can be parameterised to forecast the emergence of future events for particular scenarios. Agent-based modelling is often adopted because event-driven interactions allow collective phenomena to emerge, such as cooperation or hostility, which are important to social observations and can be challenging to gain through other approaches.…”

Intra-group Tension Under Inter-group Conflict: A Generative Model Using Group Social Norms and Identity

“…Our contribution also adds to the state-of-the-art in generative modeling of group behavior [8,9] by providing a simple but effective event driven approach. The stateof-the-art in this area is at a formative stage, with numerous interesting approaches now emerging (e.g., [10]).…”

Stability and fracture of social groups

“…Theoretical studies on group behavior have either directly focused on simple two-player ultimatum and prisoner's dilemma games [7], [8], [9], [10], [11], [12], [13], or bespoke games relevant to particular scenarios (e.g., group conflict [14], [15], [16]). Recently, Kranton [17] provided a roadmap for the integration of more complex models to create an identity-based meta-model for group behavior.…”