Data types generalization and transformation for data mining algorithms

Abstract

In most applications, knowing the characteristics of the data mining methods is usually the key factor to determine the kind of data mining methods should be applied. In this work, we first survey and analyze six kinds of data mining algorithms and four kinds of data forms, and then find out the relations between the mining algorithms and the data types. According to the relations, the suitable generalized data types will be created and is then used to transform the generalized data types of data sources to the suitable one for the selected mining algorithm. With the proposed preprocessing work for data mining algorithms, users can select appropriate mining algorithm just for the goal of application without considering the data types. Finally. two applications for e-mail management and e-mail log analysis are proposed to show the practicality of our method.