Improving performance of distributed data mining (DDM) with multi-agent system Trilok Nath Pandey 1 , Niranjan Panda 2 and Pravat Kumar Sahu 3 1 Institute of Technical Education and Research, Siksha ‘O’ Anusandhana University Khandagiri Square, Bhubaneswar-751030, Orissa, India 2 Institute of Technical Education and Research, Siksha ‘O’ Anusandhana University Khandagiri Square, Bhubaneswar-751030, Orissa, India 3 Institute of Technical Education and Research, Siksha ‘O’ Anusandhana University Khandagiri Square, Bhubaneswar-751030, Orissa, India Abstract Autonomous agents and multi-agent systems (or agents) and knowledge discovery (or data mining) are two of the most active areas in information technology. Ongoing research has revealed a number of intrinsic challenges and problems facing each area, which can't be addressed solely within the confines of the respective discipline. A profound insight of bringing these two communities together has unveiled a tremendous potential for new opportunities and wider applications through the synergy of agents and data mining. With increasing interest in this synergy, agent mining is emerging as a new research field studying the interaction and integration of agents and data mining. In this paper, we give an overall perspective of the driving forces, theoretical underpinnings, main research issues, and application domains of this field, while addressing the state-of-the-art of agent mining research and development. Our review is divided into three key research topics: agent-driven data mining, data mining-driven agents, and joint issues in the synergy of agents and data mining. This new and promising field exhibits a great potential for groundbreaking work from foundational, technological and practical perspectives. Keywords: Multi-agent Systems, Distributed Data Mining, Clustering, Privacy, Agent, DDM. 1. Introduction Multi-agent systems (MAS) often deal with complex applications that require distributed problem solving. In many applications the individual and collective behavior of the agents depend on the observed data from distributed sources. In a typical distributed environment analyzing distributed data is a non-trivial problem because of many constraints such as limited bandwidth (e.g. wireless networks), privacy sensitive data, distributed compute nodes, only to mention a few. The field of Distributed Data Mining (DDM) deals with these challenges in analyzing distributed data and offers many algorithmic solutions to perform different data analysis and mining operations in a fundamentally distributed manner that pays careful attention to the resource constraints. Since MAS are also distributed systems, combining DDM with MAS for data intensive applications is appealing. The increasing demand to scale up to massive data sets inherently distributed over a network with limited bandwidth and computational resources available motivated the development of distributed data mining (DDM). DDM is expected to perform partial analysis of data at individual sites and then to send the outcome as partial result to other sites where it is sometimes required to be aggregated to the global result. Quite a number of DDM solutions are available using various techniques such as distributed association rules, distributed clustering, Bayesian learning, classification (regression), and compression, but only a few of them make use of intelligent agents at all. The main problems any approach to DDM is challenged issues of autonomy and privacy. For example, when data can be viewed at the data warehouse from many different perspectives and at different levels of abstraction, it may threaten the goal of protecting individual data and guarding against invasion of privacy. These issues of privacy and autonomy become particularly important in business application scenarios where, for example, different (often competing) companies may want to collaborate for fraud detection but without sharing their individual customers’ data or disclosing it to third parties. One lesson from the recent research work on DDM is that cooperation among distributed DM processes may allow elective mining even with-out centralized control. This IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 2, No 3, March 2012 ISSN (Online): 1694-0814 www.IJCSI.org 74 Copyright (c) 2012 International Journal of Computer Science Issues. All Rights Reserved.