DOI QR코드

DOI QR Code

Design and Application of a Winning Forecast Model of the AOS Genre Game

AOS 장르 게임의 승패 예측 모형의 설계와 활용

  • 구지민 (덕성여자대학교 정보통계학과) ;
  • 유견아 (덕성여자대학교 컴퓨터학과)
  • Received : 2016.09.05
  • Accepted : 2016.10.27
  • Published : 2017.01.15

Abstract

Games of the AOS genre are classified as an e-sport rather than a recreational computer game. The involved statistical analyses such as game playing patterns and the season's characters gain importance due to the expertise-requiring nature of sports. In this study, the strategic analysis of computer games was conducted by using data mining techniques on League of Legend, a representative AOS game. We designed and tested a winning forecast model using winning percentage prediction techniques such as logistic regression analysis, discriminant analysis, and artificial neural networks. The game data analysis results were represented by a probabilistic graph and used in the visualization tool for game play. Experimental results of the winning forecast model showed a high classification rate of 95% on average with potential for use in establishing various strategies for game play with the visualization tool.

AOS(Aeon of Strife)장르의 게임들은 단순히 즐기는 컴퓨터 게임이 아닌 대표적인 e스포츠 종목으로 자리매김하고 있으며 전문성을 필요로 하는 스포츠의 특성상, 게임 플레이 패턴 및 시즌 별 캐릭터 선택 등 게임 운영에 필요한 통계 분석의 중요성이 증가하고 있다. 본 논문에서는 대표적인 AOS 게임 중의 하나인 리그오브레전드의 게임 데이터를 이용해 데이터 마이닝 기법을 이용한 게임의 전략적 분석을 실시한다. 통계적 승률 예측 기법인 로지스틱 회귀분석과 판별 분석 및 인공신경망을 이용하여 게임의 승패 예측 모형을 설계하고 실험한다. 게임 데이터 분석 결과는 확률을 표시한 그래프로 표현되어 게임 플레이를 돕기 위해 개발된 시각적 도구에 이용한다. 승패 예측 모형의 실험 결과, 평균적으로 95%의 높은 분류율을 보이고 시각화 도구를 통해 게임 플레이의 다양한 전략 수립에 이용됨을 보인다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Korea Council of Sport for All, Sports Encyclopedia [Online]. Available : http://portal.sportal.or.kr (downloaded 2016, Aug. 24)
  2. S.S. Oh, D.H. Kim, "Analysis of the Academic Research Trend of e-sports," Journal of Korean society for Wellness, Vol. 7, No. 2, pp. 113-121, May. 2012.
  3. B.I. Park, "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, Vol. 36, No. 1, pp. 101-120, May. 2009.
  4. H.Y. Lee, "A Study on Forecastiong the Winning Rate of Soccer Games Using the Poisson Distribution," Journal of the Korean Data Analysis Society, Vol. 14, No. 1(B), pp. 499-507, Feb. 2012.
  5. J.H. Kim, G.T. Ro, J.S. Park, W.H. Lee, "The Development of Soccer Game Win-Lost Prediction Model Using Neural Network Analysis - FIFA world cup 2006 Germany," Korean Journal of Sport Science, Vol. 18, No. 4, pp. 54-63, 2007. https://doi.org/10.24985/kjss.2007.18.4.54
  6. S.H. Gu, H.S. Kim, S.Y. Jang, "A Comparison Study on the Prediction Models for the Professional Basketball Games," Korean Journal of Sport Science, Vol. 20, No. 4, pp. 704-711, 2009. https://doi.org/10.24985/kjss.2009.20.4.704
  7. J.H. Kim, K.T. Kim, J.K. Han, "Big Data Analysis based on Deep Learning for Baseball Game Data," Proc. of Symposium of the Korean Institute of communications and Information Science, pp. 262-265, 2015.
  8. S.J Lee, D.H. Lee, "Real time predictive system design and implementation using Bigdata-log," Journal of the Korea Insitute of Information Security and Cryptology, Vol. 25, No. 6, pp. 1399-1410, Dec. 2015. https://doi.org/10.13089/JKIISC.2015.25.6.1399
  9. J.K. Kim, C.E. Wong, K.C. Jung, "Game Player Model Analysis with Time-series Data Mining," Proc. of the Korea Information Science Society 2007 Fall Conference, Vol. 34, No. 1(C), pp. 293-296, 2007.
  10. J.Y. Kim, H.J. Lee, "A Study of Gamebot Detection using Online Game Log Data Analysis," Proc. of the Korea Information Science Society 2013 Fall Conference, pp. 680-682, 2013.
  11. J.Y. Kim, H.J. Lee, "Gamebot Detecting Rule Verification and Gamebot Detection using Online Game Log Data," Proc. of the Korea Information Science Society 2014 Winter Conference, pp. 835- 837, 2014.
  12. K.Y. Lee, K.M. Jeong, "A Game Log Data Analaysis Technique using MapReduce," Journal of The Korean Society For Computer Game, Vol. 27, No. 1, pp. 19-25, Mar. 2014.
  13. League of Legend Developers Web Site, [Online]. Available: https://developer.riotgames.com/
  14. League of Legend Official Web Site, [Online]. Available: http://www.leagueoflegends.co.kr/
  15. J.H. Kim, R Multivariate statistical analysis, KyoWooSa, Seoul, pp. 154-157, 2015.