Multi-Agent System for Data Classification from Data Mining using SVM

Most of the databases are multi-relational, but the existing data mining approaches verify the classification rules in a single data relation. This paper introduces an efficient algorithm for mining important classification rule for multi-relational database using distributed data mining ideas. To achieve this, an Intelligent Agent is used. An Intelligent agent is an entity that observes and acts upon an environment to achieve its goal. We have implemented a novel distributed data mining method to mine(classify) important rules in multiple relations and to improve efficiency of the mining, we have combined Support Vector Machines (SVM) algorithm. This arrangement is useful for classifying the details from different sources based on support vector machine's algorithm.