Service-Oriented Distributed Data Mining

摘要

Data mining research currently faces two great challenges: how to embrace data mining services with just-in-time and autonomous properties and how to mine distributed and privacy-protected data. To address these problems, the authors adopt the Business Process Execution Language for Web Services in a service oriented distributed data mining (DDM) platform to choreograph DDM component services and fulfill global data mining requirements. They also use the learning-from-abstraction methodology to achieve privacy-preserving DDM. Finally,they illustrate how localized autonomy on privacy-policy enforcement plusa bidding process can help the service-oriented system self-organize.