WIT Press


Kernel Discriminant Analysis And Information Complexity: Advanced Models For Micro-data Mining And Micro-marketing Solutions

Price

Free (open access)

Paper DOI

10.2495/DATA060121

Volume

37

Pages

8

Published

2006

Size

348 kb

Author(s)

C. Liberati & F. Camillo

Abstract

In this paper we shall consider Kernel Discriminant Analysis as an innovative tool for supervised classification in a business vision as a marketing solution. The main idea we propose is the combined use of information complexity and bootstrap process which allows the user to overcome the open problems of such a technique as the kernel function choice and at the same time check the robustness of the rule found. Keywords: Kernel Discriminant Analysis, information-theoretic complexity measure, bootstrap process, micro-data mining, marketing solution. 1 From data mining to data base marketing Today, more than in the past, companies understand the value of collecting customer data which try to exploit an intelligent system for extracting interesting information. The need for a business to get knowledge from data comes from demand to monitor its own clients in order to preserve its relationship with its customers. In fact, the scenario with which a business has to face today is really complex: many customers, many products, many competitors, and little time to react, it means that customer loyalty is a thing of the past so a company needs to reinforce the value of its brand providing specific products projected \“around the customers”. So it is clear how in such situations the use of Data Mining (DM) in a Knowledge Discovery process (KDD) is dramatically important [1]. The role of DM therefore consists of helping a company to solve vexing issues and to address business processes to reach a good impact in the market. Data mining, on

Keywords

Kernel Discriminant Analysis, information-theoretic complexity measure, bootstrap process, micro-data mining, marketing solution.