Penerapan Metode Generalized Multivariate Decision Tree pada Data Permainan Auto Chess Mobile Online

Yusuf Rafsanjani, Suliadi Suliadi

Abstract


Abstract. Game Auto Chess Mobile, is a strategy game played by 8 players in one game. The game develops conventional chess games using unique pawn combinations available in the game. There are 10 unique pawn classes, players with the best combination of pawn classes will be the winners in The Auto Chess Mobilegame. Based on the phenomenon, the problems in this study are formulated as follows: (1) can the Generalized Multivariate Decision Tree method be applied to Auto Chess Mobile game history data? (2) How to predict the results of matches in Auto Chess Mobile using the Generalized Multivariate Decision Tree method based on Game History Data?. Researchers used the Generalized Multivariate Decision Tree method using a quantitative approach. The population selected in this study was 504 players of Auto Chess Mobile Online who were observed twice for each player. The results of this study are: (1) The Generalized Multivariate Decision Tree method can be applied to classify the results of Auto Chess Mobile games. (2) The Generalized Multivariate Decision Tree method results in classification accuracy of 73.4 percent for training data and 53.8 percent for data testing.

Keywords: Prediction, Generalized Multivariate Decision Tree, Auto Chess Mobile Online.

Abstrak. Permainan Auto Chess Mobile, merupakan permainan strategi yang dimainak oleh 8 pemain dalam satu pertandingan. Permainan ini mengembangkan permainan catur konvensional dengan menggunakan kombinasi bidak unik yang tersedia dalam permainan. Terdapat 10 kelas bidak yang unik, pemain dengan kombinasi kelas bidak terbaik akan menjadi pemenang dalam permainan Auto Chess Mobile. Berdasarkan fenomena tersebut, maka permasalahan dalam penelitian ini dirumuskan sebagai berikut: (1) apakah metode Generalized Multivariate Decision Tree dapat diterapkan pada data riwayat permainan Auto Chess Mobile? (2) bagaimanakah prediksi hasil pertandingan pada permainan Auto Chess Mobile menggunakan metode Generalized Multivariate Decision Tree berdasarkan Data Riwayat Permainan?. Peneliti menggunakan metode Generalized Multivariate Decision Tree dengan menggunakan pendekatan kuantitatif. Populasi yang dipilih dalam penelitian ini adalah pemain permainan Auto Chess Mobile yang berjumlah 504 pemain yang diamati sebanyak 2 kali untuk setiap pemain. Hasil dari penelitian ini adalah: (1) Metode Generalized Multivariate Decision Tree dapat diterapkan untuk mengklasifikasikan hasil permainan Auto Chess Mobile. (2) Metode Generalized Multivariate Decision Tree menghasilkan ketepatan klasifikasi sebesar 73.4 persen untuk data training dan 53.8 persen untuk data testing.

Kata Kunci: Prediksi, Generalized Multivariate Decision Tree, Auto Chess Mobile.


Keywords


Prediction; Generalized Multivariate Decision Tree; Auto Chess Mobile Online.

References


Breiman, L., J. H. Friedman, R. A. Olshen, and C. J. Stone. (1984). Classification and Regression Trees. Wadsworth Inc.

Istianto, Roni. 2019. Guide Bermain Game Auto Chess Mobile Online Bagi Pemula. https://gamebrott.com/guide-bermain-game-auto-chess-Mobile Online-bagi-pemula. (Diakses tanggal 5 Januari 2019)

Lee, S. K (2014). On Classification and Regression Trees for Multiple Responses 1113-1130.

Lewis, M.D dan Roger, J. (2000). An Introducion to Classification and Regression Trees (CART) Analysis. Annual Meeting of Society for Academic Emergency. California, UCLA Medical Centeres.

Liang, K. Y. and S. L. Zeger, Longitudinal Data Analysis using Generalized Linear Models, Biometrika, 73, 1986, pp13-22

Pratiwi, F.E dan Zain. (2014). Klasifikasi Pengangguran Terbuka Menggunakan CART (Classifiation and Regression Tree) di Provinsi Sulawesi Utara. Program Sarjana, Jurusan Statistika, FMIPA, Institut Teknologi Sepuluh Nopember (ITS).

Segal, M. R. (1992). "Tree-Structured Methods for Longitudinal Data," Journal of the American Statistical Association, 87, 407-418.

Webb, P., and Yohannes. (1999). Classification and Regression Trees, CART. International Food Policy Research Institute. Washington D.C.

Yunindya, Rifani. 2017. Model credit Scoring Menggunakan Metode Classification and Regression Trees (CART) pada Data Kartu Kredit. Skripsi Prodi Statistika Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Islam Bandung.

Zhang, H. P. (1998). "Classification Tree for Multiple Binary Responses," Journal of the American Statistical Association, 93, 180-193.

Zulfa W, Mardika, Moch Abdul Mukid, Hasbi Yasin (2016). "Pembentukan Pohon Klasifikasi Biner Dengan Algoritma Cart (Classification and Regression Trees) (Studi Kasus: Kredit Macet Di Pd. Bpr-bkk Purwokerto Utara)" Jurnal Gaussian, vol. 5, no. 3, 30 Aug. 2016, pp. 583-592.




DOI: http://dx.doi.org/10.29313/.v6i2.23502

Flag Counter