Decision Theory Research and Development -- Risk-Advised Prediction

We propose to design a very powerful technology to support actor modeling and behavior prediction of arbitrary individual and social actors, all guided by risk analysis calculations. Users without formal background in psychology, social theory, or decisiontheory will be able to develop actor models relevant to contemplated risks, and form predictions about actor behavior. Predictions serve to validate the models and, once accepted, to inform the development of indications and warnings.The actor modeling technology will enable users to summarize observations about human activity (individual, social) in the form of generative practices: computations that reproduce the observations if handed the right conditions, and that predict howbehavior is produced and adapted in related situations. Practices enable prediction of actor behavior for situations that have not been observed; we have proven the viability of our modeling approach in other work.This technology rests on Synergia?s Event and Activity Capture technology, used to encode observations about human activity using a representation we have invented: hierarchical event-behavior graphs.Predictions are delivered to Bayesian networks or decision graphs. In the latter case Synergia has invented diagnostic calculations that legislate which parts of the decision structure (not just parametric structure!) are rational to improve. Defense, public-sector, and private-sector activities are becoming more complex, and more inter-dependent in their execution. Risks and opportunity management are extremely sensitive to timely decision-making and action. Prediction of the activities ofothers is essential in modern threat environments, and equally, in the private sector.We will create a new technology to support risk-advised modeling and prediction of the likely capabilities and intentions of arbitrary individuals and social actors (e.g., organizations, culture). The technology will enable modeling and prediction based onpsychological, cultural, ideological, and institutional factors, rather than doctrine or 'company policy'.