Abstract—The tourism industry is growing up and competing relatively high. In Thailand, tourism is one of the main industries that can generate a large amount of domestic turnover rate. And tourist information in Thailand is stored in large quantities. It is difficult to understand the needs of tourists. Therefore, this study presents segmentation of domestic tourist in Thailand by combining attribute weight with clustering algorithm. The study used two step algorithms, in the first step, Self-Organizing Maps (SOM) was used to determine the optimum number of clusters which an input parameter to K-Means and Fuzzy C-Means. Then, using SOM, K-Means and Fuzzy C-Means algorithms combine with feature weighting techniques based on Correlation Coefficient (CC), Information Gain Ratio (IGR), Gini Index and Principal Components Analysis (PCA) for clustering the tourists clusters. The quality of cluster was measured by Davies Bouldin Index (DB), Root Mean Square Standard Deviation (RMSSTD) and R Square (RS). The results of this study might be used for tourism management and entrepreneur tour and travel can be used for decision making and business planning.
 

Index Terms—domestic tourism, clustering, attribute weight, SOM, K-means, fuzzy C-means

Cite: Prapassorn Hayamin and Anongnart Srivihok, "Segmentation of Domestic Tourist in Thailand by Combining Attribute Weight with Clustering Algorithm," Vol. 9, No. 2, pp. 39-44, May 2018. doi: 10.12720/jait.9.2.39-44