Distributed Data Mining: The JAM system architecture

Prodromidis, Andreas L.; Stolfo, Salvatore; Tselepis, Shelley; Truta, Terrance; Sherwin, Jeffrey; Kalina, David

This paper describes the system architecture of JAM (Java Agents for Meta-learning), a distributed data mining system that scales up to large and physically separated data sets. An earlyversion of the JAM system was described in Stolfo-et-al-97-KDD-JAM. Since then, JAM has evolved both architecturally and functionally and here we present the final design and implementation details of this system architecture. JAM is an extensible agent-based distributed data mining system that supports the remote dispatch and exchange of agents among participating datasites and employs meta-learning techniques to combine the multiple models that are learned. One of JAM's target applications is fraud and intrusion detection in financial information systems. A brief description of this learning task and JAM's applicability and summary results are also discussed.



More About This Work

Academic Units
Computer Science
Department of Computer Science, Columbia University
Columbia University Computer Science Technical Reports, CUCS-007-01
Published Here
April 22, 2011