Original Research

The use of neural networks and rule induction for customer segmentation and target market profiling

J. Z. Bloom
South African Journal of Economic and Management Sciences | Vol 5, No 1 | a2673 | DOI: https://doi.org/10.4102/sajems.v5i1.2673 | © 2018 J. Z. Bloom | This work is licensed under CC Attribution 4.0
Submitted: 09 July 2018 | Published: 31 March 2002

About the author(s)

J. Z. Bloom, Department of Business Management, University of Stellenbosch, South Africa

Full Text:

PDF (1MB)

Share this article

Bookmark and Share

Abstract

Inadequate market segmentation and clustering problems could cause an enterprise to either miss a strategic marketing opportunity or not cash in on a tactical campaign. The need for in-depth knowledge of customer segments and to overcome the limitations of non-linear problems require a different approach. The objectives of the research are (1) to consider the use of self-organising feature (SOM) neural networks for segmenting tourist markets and (2) to assess the use of inducing decision trees to obtain rules for profiling existing and classifying new respondents. The findings of the SOM neural network modelling indicate three definitive natural clusters. The induction of rules from decision trees were used to obtain a broad indication of a segment profile on the basis of a rule set and also enables the segment classification of customers from follow-up surveys.

Keywords

No related keywords in the metadata.

Metrics

Total abstract views: 251
Total article views: 97


Crossref Citations

No related citations found.