Multi-hierarchical dynamic Bayesian network classifier for operational risk early-warning

At present, the methods of risk warning emphasize static function dependency or dynamic propagation of time series so that the static and dynamic information can not be consistently combined. In this paper, a dynamic multi-hierarchical Bayesian network classifier is developed for warning operational risk. And an example is presented to explain the process of operational risk early-warning and method of contribute analysis to risk rank forecast. This model has universality and can be widely used to the risk warning of other domain.