A new suite of Bayesian decision support systems is being designed to help teams who are striving to frustrate and pursue people radicalised into planning acts of extreme violence. Filters are being developed which can synthesise and present the associated vast and patchy data streams in an intelligent and user led way. These systems are designed to help in the early detection of those planning to perpetrate violent acts against the general public.

Explaining the science

The models in this project are based on established Bayesian decision support technologies - which have been successfully applied to a variety of analogous dynamic settings. The three-level model produced enables synthesis of the expert judgments of the domain experts with the streaming, but patchy, real time electronic observations concerning specific suspects.

At the deepest hidden level of this hierarchy lies a new customised family called the reduced dynamic chain event graph (RDCEG) recently developed by the PI for specifically modelling such population processes. These express as graphs an expert’s natural language hypotheses about the various different ways people in certain radicalised states might develop; translating such hypotheses into families of probability models. 

At an intermediate level are further expert judgments about the tasks someone at a particular stage of preparing a violent attack might need to perform. The final surface layer – usually the only one directly, albeit partially observable – describes what people might actually do to perform such tasks. This provides the final probabilistic layer, linking data streams to tasks and hence to states. 

These three levels then synthesise into a single probability model of the whole process. This enables the user to calculate expected utility scores that can then help to guide the appropriate deployment of resources, to ideally deter or diffuse potential attacks, or otherwise to at least frustrate these.

Project aims

  • Providing decision support in policing assault criminals – focusing especially on those radicalised into acts of extreme violence
  • Developing and refining the models described in 'Explaining the science'
  • Demonstrating to potential users the efficacy of the models to forecast and control violent extremism within the general population
  • Developing methodology to support the fast assimilation of streaming data both in the pursuit of individual suspects and populations of the same


Currently in close collaboration with various government agencies on this project. The possible beneficiaries of this work are government itself, social policy analysts, social workers, police, probation services, prison services and security and defence.


Researchers and collaborators

Contact info

[email protected]