KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Predicting Win-Loss of League of Legends Using Bidirectional LSTM Embedding

양방향 순환신경망 임베딩을 이용한 리그오브레전드 승패 예측

  • 김철기 (숭실대학교 융합소프트웨어학과) ;
  • 이수원 (숭실대학교 소프트웨어학부)
  • Received : 2019.08.23
  • Accepted : 2019.12.04
  • Published : 2020.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

E-sports has grown steadily in recent years and has become a popular sport in the world. In this paper, we propose a win-loss prediction model of League of Legends at the start of the game. In League of Legends, the combination of a champion statistics of the team that is made through each player's selection affects the win-loss of the game. The proposed model is a deep learning model based on Bidirectional LSTM embedding which considers a combination of champion statistics for each team without any domain knowledge. Compared with other prediction models, the highest prediction accuracy of 58.07% was evaluated in the proposed model considering a combination of champion statistics for each team.

e-sports는 최근 꾸준한 성장을 이루면서 세계적인 인기 스포츠 종목이 되었다. 본 논문에서는 e-sports의 대표적인 게임인 리그오브레전드 경기 시작 단계에서의 승패 예측 모델을 제안한다. 리그오브레전드에서는 챔피언이라고 불리는 게임 상의 유닛을 플레이어가 선택하여 플레이하게 되는데, 각 플레이어의 선택을 통하여 구성된 팀의 챔피언 능력치 조합은 승패에 영향을 미친다. 제안 모델은 별다른 도메인 지식 없이 플레이어 단위 챔피언 능력치를 팀 단위 챔피언 능력치로 임베딩한 Bidirectional LSTM 임베딩 기반 딥러닝 모델이다. 기존 분류 모델들과 비교 결과 팀 단위 챔피언 능력치 조합을 고려한 제안 모델에서 58.07%의 가장 높은 예측 정확도를 보였다.

Keywords

References

  1. Hyun Seong and Woojin Chang, "Forecasting the Results of Soccer Matches Using Poisson Model," IE interfaces, Vol.20, No.2, pp.133-141, 2007.
  2. Hosang Kim, Jonghwan Won, and Dae-Ki Kan, "Modelling and Predicting 2010-2012 K-League Association Football Matches Using Poisson Model Analysis," in Proceedings of the IEEK Conference, pp.1572-1575, 2014.
  3. Young Gun Choi and Hyoung Moon Kim, "A Statistical Study on Korean Baseball League Games," The Korean Journal of Applied Statistics, Vol.24, No.5, pp.915-930, 2011. https://doi.org/10.5351/KJAS.2011.24.5.915
  4. Cha Yong Kim, "A Win, Loss Predicting Model by Analyzing Professional Baseball Game," Journal of Sport and Leisure Studies, Vol.16, pp.807-819, 2001.
  5. Sea-Joong Kim, Chong-Kwan Heo, and Jae-Hyun Do, "Analysis on the Korean basketball league using data mining," Journal of The Korean Society of Sports Science, Vol.19, No.2, pp.1413-1420, 2010.
  6. Jong-Hun Kim, Kyung-Tae Kim, and Jong-Ki Han, "Big Data Analysis based on Deep Learning for Baseball Game Data," in Proceedings of the Korean Institute of Communication Sciences Conference, pp.262-265, 2015.
  7. Yeong-Jin Seo, Hyung-Woo Moon, and Yong-Tae Woo, "A Win/Lose prediction model of Korean professional baseball using machine learning technique," Journal of the Korea Society of Computer and Information, Vol.24, No.2, pp.17-24, 2019. https://doi.org/10.9708/JKSCI.2019.24.02.017
  8. Ji-Min Ku and Kyeonah Yu, "Design and Application of a Winning Forecast Model of the AOS Genre Game," KIISE Transactions on Computing Practices, Vol.23, No.1, pp. 37-44, 2017. https://doi.org/10.5626/KTCP.2017.23.1.37
  9. Antonio Luis Cardoso Silva, Gisele Lobo Pappa, and Luiz Chaimowicz, "Continuous Outcome Prediction of League of Legends Competitive Matches Using Recurrent Neural Networks," 2018. http://www.sbgames.org/sbgames2018/files/papers/ComputacaoShort/188226.pdf.
  10. Alexander Neumann, "Developing a Model to Predict Match Outcomes in League of Legends," Barrett, The Honors College Thesis, Arizona State University, 2015.
  11. Cheolgi Kim and Soowon Lee, "Predicting Win-Loss of League of Legends at the Start of the Game using Machine Learning Techniques," in Proceedings of the ISSAT DSBFI. pp.28-30, 2019.
  12. Chi-Yun Song, Sung-Min Yang, and Sangwoo Kang, "Namedentity Recognizer Based on Bidirectional LSTM CRFs Using Improved Word Embedding Models And Dictionaries," in Proceedings of the Korean Information Science Society Conference, pp.699-701. 2017.
  13. Seung-Hoon Na, and Jinwoo Min, "Character-based LSTM CRFs for named entity recognition," in Proceedings of Korean Institute of Information Scientists and Engineers, pp.729-731, 2016.
  14. Jianri Li, EuiHyeon Lee, and Jong-Hyeok Lee, "Sequenceto- sequence based Morphological Analysis and Part-Of-Speech Tagging for Korean Language with Convolutional Features," Journal of Korean Institute of Information Scientists and Engineers, Vol.44, No.1, pp.57-62, 2017.
  15. League of Legends Developers Web Site [Online], Available: https://developer.riotgames.com/.
  16. 리그오브레전드 챔피언 통계 [Internet], http://fow.kr/champs/.