Integrating decision trees and cognitive maps for market segmentation in service sector

Sadic S., Kayakutlu G.

Conference of the Portland-International-Center-for-Management-of-Engineering-and-Technology (PICMET 2007), Oregon, United States Of America, 5 - 09 August 2007, pp.2748-2754 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/picmet.2007.4349612
  • City: Oregon
  • Country: United States Of America
  • Page Numbers: pp.2748-2754
  • Istanbul Technical University Affiliated: Yes


Customer data is the key to the marketing success and this is why data mining has become an inevitable tool. Data mining is used to detect the knowledge in the accumulated data for which various analytical methods are used. The knowledge is further used to support the predictions for the future of the customer portfolio. This study aims to illustrate a framework for integrated implementation of cognitive maps and decision trees in the development of customer segments. The first step is to identify the company specific factors, which are effective in marketing. The second step is to determine the interactions among these factors through a cause and effect map, which enables the classification of the data. As the third step decision trees are developed, based on these classes and the data. The last step is the preparation of customer segments to be used by sales and marketing departments. This paper also represents a pilot application of the framework in a digital TV channel trying to market subscriptions. This study will not only contribute in data mining field but also in customer relations.