Abstract: A system and method that generates a hierarchical tree network and uses linear-plus-nonlinear learning algorithms to form a consensus view on a member's future health status. Each leaf in the hierarchical tree network is homogeneous in clinical characteristics, experience period, and available data assets. Optimization is performed on each leaf so that features and learning algorithms can be tailored to local characteristics specific to each leaf.

Abstract: An information collection and processing system and related automated method for use by an organization providing health care to a given population. The system includes an arrangement for storing information relating to a plurality of contractual relationships existing between the organization, a plurality of health care providers, and a plurality of payors. The storage arrangement also includes information relating to a plurality of patients in the given population, and information relating to transactions between the organization, providers and the payors.