Shonali Krishnaswamy, Arkady Zaslavsky
Seng Wai Loke
The emergence of Application Service Providers hosting Internet-based data mining services is being seen as a viable alternative for organisations that value their knowledge resources but are constrained by the high cost of data mining software. In this paper, we present a new multiple service provider model of operation for the Internet delivery of data mining services. This model has several advantages over the currently predominant approach for delivering data mining, services such as providing clients with a wider variety of options, choice of service providers and the benefits of a more competitive marketplace. We have developed XML DTD’s to support the interaction protocols for the multiple service provider model including: specification of the task preferences of clients, specification of the functionality of data mining service providers and the exchange of information to access data and computational resources to perform the task. We have also developed a matching algorithm to map the task preferences of the client preferences to the functionality of the data mining service providers.