Effective Behavioral Modeling and Prediction Even When Few Exemplars are Available

The most critical limitation of existing approaches to behavior modeling and prediction is their inability to support the required knowledge modeling and continuing refinement under realistic constraints (e.g., few historic exemplars, the lack of knowledge engineering support, and the need for rapid system deployment and constant adaptation). The proposed Propheteer systems will directly address this shortcoming through three primary techniques. First, with Propheteer we abandon the typical consensus-driven modeling approach in favor of an approach that solicits asynchronous knowledge contributions (in the form of alternative future scenarios and indicators) without burdening the user with endless certainty or probability estimates. Second, we enable knowledge contributions by personnel beyond the typical core decision making group, thereby casting light on blindspots, mitigating human biases, and helping maintain the currency of the developed behavior models. Last, we propose to motivate knowledge contributions by supporting capabilities that go beyond the central threat modeling and prediction tasks, such as current situation monitoring and context enhanced search. In this Phase II we will build on the strong foundation established in Phase I to construct and field our new technology for matching Information Operations needs with solutions and proceed toward successful commercialization.