Date Classification through integration of Sequential process involving Data cleaning, attribute oriented induction, Relevance analysis as preprocessor to induction of decision tree USING RELATIONAL DATABASE

摘要

Classification, i.e. classifying unknown values of certain attributes of interest based on the values of other attributes, is a major task in data mining. A well accepted method of classification is the induction of decision tree. However, since this approach perform classification on primitive data stored in the database; it inherits the problems such as difficulties in handling large amounts of data and continuous numerical values, the tendency to favor many-valued attributes in the selection of determinant attribute, etc. Also the efficiency of existing decision tree algorithms has been well established for relatively small data sets. In data mining applications, very large training sets are common. Hence, this restriction limits the scalability of such algorithms. Also in most data mining application, users have a little knowledge regarding which attribute should be selected for effective mining. In this paper, we address above issues by proposing a data classification method which integrates data cleaning, attribute oriented induction, relevance analysis and induction of decision trees. This method extracts rules at multiple levels of abstraction and handles large data sets and continuous numerical values in a scalable way.