pp. 2697-2707
S&M2294 Research Paper of Special Issue https://doi.org/10.18494/SAM.2020.2800 Published: August 20, 2020 Combination of Self-organizing Map and k-means Methods of Clustering for Online Games Marketing [PDF] Shaoyong Yu, Mei Yang, LinHai Wei, Jian-Shiun Hu, Hsien-Wei Tseng, and Teen-Hang Meen (Received January 10, 2020; Accepted July 10, 2020) Keywords: data mining, SOM, k-means, online games, market segmentation
Data mining has been applied in many fields, such as pattern evaluation, image recognition, and data analysis. Clustering is one of the most popular methods of data mining. There are many algorithms concerning clustering, such as k-means and Farthest First in data mining fields, and adaptive resonance theory (ART) and self-organizing map (SOM) in machine learning. ART and SOM are unsupervised learning algorithms, which better determine the best numbers for clustering than only the k-means algorithm. This study is devoted to applying a combination of SOM with k-means to study the marketing of online games in Taiwan. The results show that the marketing segmentation of online games can be evaluated well by clustering the users’ data obtained from any online or offline survey. The method that combines SOM with k-means has been shown in this study to provide a good evaluation of the market segmentation.
Corresponding author: LinHai Wei, Teen-Hang MeenThis work is licensed under a Creative Commons Attribution 4.0 International License. Cite this article Shaoyong Yu, Mei Yang, LinHai Wei, Jian-Shiun Hu, Hsien-Wei Tseng, and Teen-Hang Meen, Combination of Self-organizing Map and k-means Methods of Clustering for Online Games Marketing, Sens. Mater., Vol. 32, No. 8, 2020, p. 2697-2707. |