Abstract: A system, computer program product, and method provide for reason driven data analysis in a web-based system that is configurable to various types of data and environments. The computer program product provides for navigation of a report tree of reports that are hierarchically organized with respect to reasons derived from an analysis of transactional data in a database. A frame based interface provides for easy and flexible navigation and configuration of the reports and other features. A configuration file is used to rapidly develop and customize the web-based system. Case management functionality is included to allow for management of cases being reviewed using the system.

Abstract: Computer implemented processes and software products generate profiles of entities, such as providers, clients, merchants and customers, and entities comprising interacting pairs of entities. The processes including deriving direct profiles from transaction data pertaining to an entity and enhancing the profile of one entity using the profile of another entity. Parallel and serial applications of the derive and enhance processes on various individual and multiple entites yields enhanced profiles that powerfully describe the interactions and relationship of the entities to each other, and between their members.

Abstract: An automated system and method detects fraudulent transactions using a predictive model such as a neural network to evaluate individual customer accounts and identify potentially fraudulent transactions based on learned relationships among known variables. The system may also output reason codes indicating relative contributions of various variables to a particular result. The system periodically monitors its performance and redevelops the model when performance drops below a predetermined level.

Abstract: An automated system and method detects fraudulent transactions using a predictive model such as a neural network to evaluate individual customer accounts and identify potentially fraudulent transactions based on learned relationships among known variables. The system may also output reason codes indicating relative contributions of various variables to a particular result. The system periodically monitors its performance and redevelops the model when performance drops below a predetermined level.