The Application of SOM Network to Clustering Enterprises Based on Questionnaires

Abstract

The self-organizing map (SOM) is an excellent tool for data mining. In order to know the understanding of businesses of establishing the environment-friendly enterprise, we carried out a questionnaire to 49 manufacturing enterprises in a city and clustered the results using SOM network. We found that there are four different classes among the enterprises. In doing this work we developed a new procedure of uniting one-dimensional SOM with two-dimensional SOM for visualizing and exploring properties of the training results. The procedure can reduce subjective factors and give satisfactory cluster results. This study was a trial applying the SOM method to cluster based on the questionnaire results directly.