Developing Multiple Sub Functions Per Association Function For Data Mining System

Abstract

Most of the existing data mining systems specialize in one data mining functions or just one approach of data mining functions. But many problems may require users to try a few different minimum functions so that they can be shown to be more effective for different kinds of data. Hence this paper focuses on introducing multiple sub functions per association function in data mining tools. To fulfill this requirement, it designs functions for discovering multiple level associations rules, two-dimensional optimized gain rules and synthesized association rules from huge databases. The intelligent performance of existing systems can be improved by the incorporation of such added features.