ISHS Acta Horticulturae 566: II International Symposium on Application of Modelling as an Innovative Technology in the Agri-Food Chain; MODEL-IT
A COMPARISON OF SOM NEURAL NETWORKS AND K-MEANS CLUSTERING USING REAL WORLD DATA: CHINESE CONSUMER ATTITUDES TOWARDS IMPORTED FRUIT |
| Authors: | X. Sun, R. Collins, J. Kim |
| Keywords: | Market segmentation, discriminant analysis, reliability tests, consumer behavior, clustering |
| Abstract:
SOM neural networks are regarded as a new clustering technique in market research. However for the technique to be widely adopted in practice, it should demonstrate superiority over traditional clustering methods. In this research we compared SOM neural networks with K-means algorithms to test their relative ability to generate reliable clustering solutions using real world data - Chinese consumer attitudes towards imported fruit. Results show that K-means performs better than SOM in terms of reliability, but SOM’s strength is its ability to discover the “natural” number of clusters. | |
Download Adobe Acrobat Reader (free software to read PDF files) | |
