Hierarchical Analysis for Discovering Knowledge in Large Databases

Abstract

This article presents a goal-question-metric paradigm for selecting and implementing metrics for data mining, as well as a case study to illustrate that paradigm. the aim of this technique is to increase customer satisfaction and retention rate. It is especially useful for transaction records that are incomplete and therefore cannot be used as is for data mining. By analyzing the company's goal and strategies, data mining rules can be developed to discover associations within the available data.