Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Development of game indicators and winning forecasting models with game data

게임 데이터를 이용한 지표 개발과 승패예측모형 설계

  • Ku, Jimin (Department of Information and Statistics, Duksung Women's University) ;
  • Kim, Jaehee (Department of Information and Statistics, Duksung Women's University)
  • 구지민 (덕성여자대학교 정보통계학과) ;
  • 김재희 (덕성여자대학교 정보통계학과)
  • Received : 2017.01.11
  • Accepted : 2017.03.14
  • Published : 2017.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

A new field of e-sports gains the great popularity in Korea as well as abroad. AOS (aeon of strife) genre games are quickly gaining popularity with gamers from all over the world and the game companies hold game competitions. The e-sports broadcasting teams and webzines use a variety of statistical indicators. In this paper, as an AOS genre game, League of Legends game data is used for statistical analysis using the indicators to predict the outcome. We develop new indicators with the factor analysis to improve existing indicators. Also we consider discriminant function, neural network model, and SVM (support vector machine) for make winning forecasting models. As a result, the new position indicators reflect the nature of the role in the game and winning forecasting models show more than 95 percent accuracy.

스포츠의 새로운 분야로 자리 잡고 있는 e-스포츠는 국내 뿐 아니라 해외에서도 많은 인기를 얻고 있다. 그 중 AOS (aeon of strife) 장르의 게임들은 대표적인 e-스포츠 대회 중 하나로 주목받으며, 방송 및 미디어 매체는 다양한 통계 지표를 활용한 게임 중계를 실시하고 있다. 본 논문에서는 AOS 장르의 게임인 리그오브레전드의 게임 데이터를 이용한 통계적 분석으로 게임 내 지표를 개선하고 승패예측을 위한 승패예측모형을 설계한다. 인자 분석을 통해 구한 인자로 기존의 지표를 개선하는 새로운 지표를 창출하고, 판별 분석, 인공신경망, SVM을 이용한 승패예측모형을 추정해 모형 간 비교를 실시하였다. 그 결과, 게임 내 포지션의 특성을 반영한 인자 점수로 새로운 지표를 제안하였으며, 세 가지 승패예측모형은 모두 평균 95% 의 높은 정분류율을 보였다.

Keywords

References

  1. Cho, D. (2016) The winning probability in Korean series of Korean professional baseball. Journal of the Korean Data & Information Science Society, 27, 663-676. https://doi.org/10.7465/jkdi.2016.27.3.663
  2. Gu, S. H., Kim, H. S. and Jang, S. Y.(2009). A comparison study on the prediction models for the professional basketball games. Korean Journal of Sport Science, 20, 704-711. https://doi.org/10.24985/kjss.2009.20.4.704
  3. Hastie, T., Tibshirani, R. and Friedman, J. (2001). The elements of statistical learning, Springer Verlag, Germany.
  4. Kang, B., Huh, M. and Choi, S. (2015) Performance analysis of volleyball games using the social network and text mining techniques. Journal of the Korean Data & Information Science Society, 26, 619-630. https://doi.org/10.7465/jkdi.2015.26.3.619
  5. Kim, J. H. (2015). R multivariate statistical analysis, Kyowoosa, Seoul.
  6. Kim, J. Y. and Lee, H. J. (2013). A study of gamebot detection using online game log data analysis. Proceedings of the Korea Information Science Society 2013 Fall Conference, 680-682.
  7. Kim, J. Y. and Lee, H. J. (2014). Gamebot detecting rule verification and gamebot detection using online game log data. Proceedings of the Korea Information Science Society 2014 Winter Conference, 835-837.
  8. Kim, S.-K. and Lee, Y.-H. (2016) The estimation of winning rate in Korean professional baseball league. Journal of the Korean Data & Information Science Society, 27, 653-661. https://doi.org/10.7465/jkdi.2016.27.3.653
  9. Kim, S. H. and Lee, J. W. (2012). Estimating the determinants of victory and defeat through analyzing records of Korean pro-basketball. Journal of the Korean Data & Information Science Society, 23, 993-1003. https://doi.org/10.7465/jkdi.2012.23.5.993
  10. Kim, S. M. and Kim, H. K. (2015). A research on improving client based detection feature by using server log analysis in FPS games. Journal of the Korea Institute of Information Security and Cryptology, 25, 1465-1475. https://doi.org/10.13089/JKIISC.2015.25.6.1465
  11. Korea Council of Sport for All, Sports Encyclopedia, Available: http://portal.sportal.or.kr (downloaded 2016, Aug. 24).
  12. League of Legend Developers Web Site, Available: https://developer.riotgames.com/.
  13. Lee, C. S. (2008). Evaluation model of on-line game using analytic hierarchy process. Journal of Global E-Business Association, 9, 109-127.
  14. Oh, S. S. and Kim, D. H. (2012). Analysis of the academic research trend of e-sports. Journal of Korean Society for Wellness, 7, 113-121.
  15. Park, B. I. (2009). e-Sports value and the controversial issues and solutions for a problem of e-Sports from a sportive point of view. Journal of Sport and Leisure Studies, 36, 101-120.
  16. Ryu, S. I. and Park, S. J. (2009). Indicator analysis and prediction methods of online games using parametric method and Fourier analysis. Proceedings of Asia Pacific Journal of Information Systems, 2, 466-481.

Cited by

  1. 비김이 있는 연속적인 게임에 관한 연구 vol.28, pp.4, 2017, https://doi.org/10.7465/jkdi.2017.28.4.783
  2. 게임데이터를 이용한 승패예측 및 세분화된 변수 중요도 도출 기법 vol.5, pp.2, 2017, https://doi.org/10.36498/kbigdt.2020.5.2.231
  3. 기계학습을 활용한 게임승패 예측 및 변수중요도 산출을 통한 전략방향 도출 vol.21, pp.4, 2021, https://doi.org/10.7583/jkgs.2021.21.4.3