KLASTERISASI KARAKTERISTIK PEMAIN GAME BERDASARKAN PREFERENSI FITUR DAN MODEL BISNIS MENGGUNAKAN K-MEANS
Keywords:
Data Mining, K-Means Clustering, Monetisasi Game, Perilaku Pemain, Segmentasi PemainAbstract
Perkembangan industri game di Indonesia mendorong pergeseran menuju model monetisasi berkelanjutan, seperti mikrotransaksi, yang memengaruhi preferensi dan perilaku pemain. Penelitian ini bertujuan mengelompokkan pemain game di Indonesia berdasarkan preferensi fitur game, preferensi monetisasi, dan perilaku aktual menggunakan algoritma K-Means Clustering. Data diperoleh dari 112 responden melalui kuesioner daring dan dianalisis menggunakan Elbow Method serta Silhouette Score untuk menentukan jumlah klaster optimal. Hasil penelitian menunjukkan lima klaster terbaik (k=5) dengan Silhouette Score sebesar 0,497, yaitu Pemain Aktif High-Spending, Pemain Anti-Monetisasi, Pemain Story-Visual Enthusiast, Pemain Kompetitif-Sosial Intensif, dan Pemain Kasual Moderat. Penelitian ini menyimpulkan bahwa karakteristik pemain game bersifat heterogen, sehingga pengembang perlu menerapkan strategi fitur dan monetisasi yang disesuaikan dengan setiap segmen pemain serta meminimalkan mekanisme pay-to-win guna menjaga keseimbangan dan kepuasan pemain.
References
[1] P. Rita, R. Ramos, and R. G. Caetano, “The role of microtransactions in impulse buying and purchase intention in the video game market,” vol. 50, 2024, doi: 10.1016/j.entcom.2024.100693.
[2] E. Gibson, M. D. Griffiths, F. Calado, and A. Harris, “Videogame player experiences with micro-transactions: An interpretative phenomenological analysis,” Comput. Human Behav., vol. 145, p. 107766, 2023, doi: 10.1016/j.chb.2023.107766.
[3] D. Zendle, R. Meyer, and N. Ballou, “The changing face of desktop video game monetisation: An exploration of exposure to loot boxes, pay to win, and cosmetic microtransactions in the most-played Steam games of 2010-2019,” 2020, doi: 10.1371/journal.pone.0232780.
[4] Y. Su, P. Backlund, and H. Engström, “Comprehensive review and classification of game analytics,” Serv. Oriented Comput. Appl., vol. 15, no. 2, pp. 141–156, 2021, doi: 10.1007/s11761-020-00303-z.
[5] Y. Qiu, Y. Gong, and G. Liu, “User Behavior Analysis and Clustering in a MMO Mobile Game: Insights and Recommendations,” pp. 1–16, 2024.
[6] Q. Zhou and B. Sun, “Adaptive K-means clustering based under-sampling methods to solve the class imbalance problem,” Data Inf. Manag., vol. 8, no. 3, p. 100064, 2024, doi: 10.1016/j.dim.2023.100064.
[7] F. Pedregosa, R. Weiss, and M. Brucher, “Scikit-learn: Machine Learning in Python,” vol. 12, pp. 2825–2830, 2011.
[8] V. Klézl and S. Kelly, “Negativists, enthusiasts and others: a typology of players in free-to-play games,” pp. 7939–7960, 2023.
[9] M. Angel, E. García-Cabrera, F. Luna-Perej, L. Sevillano-Ramos, and L. Mir, “Video game player profiles among university students: Impact of game preferences and academic background,” vol. 9, 2025, doi: 10.1016/j.caeo.2025.100280.
[10] G. K. S. Lee, “In-App Purchase Behaviour and Game Design in Mobile Gaming: A Review of Monetisation and Player Experience,” 2025.
