Advertisement

A Player Behavior Model for Predicting Win-Loss Outcome in MOBA Games

  • Xuan Lan
  • Lei Duan
  • Wen Chen
  • Ruiqi Qin
  • Timo Nummenmaa
  • Jyrki Nummenmaa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11323)

Abstract

Multiplayer Online Battle Arena (MOBA) game is currently one of the most popular genres of online games. In a MOBA game, players in a team compete against an opposing team. Typically, each MOBA game is a larger battle composed of a series of combat events. During a combat, the behavior of each player varies and the outcome of a game is determined both by the variation of each player’s behavior and by the interactions within each instance of combat. However, both the variation and interaction are highly dynamic and difficult to master, making it hard to predict the outcome of a game. In this paper, we present a player behavior model (called pb-model). The model allows us to predict the result of a game once we have collected enough data on the behaviour of the players. We first use convolution to extract the features of player behavior variation in each combat and model them as sequences by time. Then we use a recurrent neural network to process the interaction among these sequences. Finally, we combine these two structures in a network to predict the result of a game. Experiments performed on typical MOBA game dataset verify that our pb-model is effective and achieves as high as 87.85% prediction accuracy.

Keywords

Game outcome prediction Data mining Deep learning 

References

  1. 1.
    Castaneda, L.M., Sidhu, M.K., Azose, J.J., Swanson, T.: Game play differences by expertise level in dota 2, a complex multiplayer video game. IJGCMS 8(4), 1–24 (2016)Google Scholar
  2. 2.
    Nummenmaa, T.: Executable formal specifications in game development: design, validation and evolution. University of Tampere, Tampere University Press (2013)Google Scholar
  3. 3.
    Erickson, G.K.S., Buro, M.: Global state evaluation in StarCraft. In: Digital Entertainment (2014)Google Scholar
  4. 4.
    Rioult, F., Mtivier, J.P., Helleu, B., Scelles, N., Durand, C.: Mining tracks of competitive video games. AASRI Procedia 8, 82–87 (2014)CrossRefGoogle Scholar
  5. 5.
    Pobiedina, N., Neidhardt, J., del Carmen Calatrava Moreno, M., Werthner, H.: Ranking factors of team success. In: Proceedings of 22nd International World Wide Web Conference, pp. 1185–1194 (2013)Google Scholar
  6. 6.
    Nuangjumnong, T.: The influences of online gaming on leadership development. Trans. Comput. Sci. 26, 142–160 (2016)CrossRefGoogle Scholar
  7. 7.
    Drachen, A., et al.: Skill-based differences in spatio-temporal team behaviour in defence of the ancients 2 (dota 2). In: Proceedings of 2014 IEEE Games Media Entertainment, pp. 1–8 (2014)Google Scholar
  8. 8.
    Li, Q., et al.: A visual analytics approach for understanding reasons behind snowballing and comeback in MOBA games. IEEE Trans. Vis. Comput. Graph. 23(1), 211–220 (2017)CrossRefGoogle Scholar
  9. 9.
    Suznjevic, M., Matijasevic, M., Konfic, J.: Application context based algorithm for player skill evaluation in MOBA games. In: Proceedings of 2015 International Workshop on Network and Systems Support for Games, pp. 1–6 (2015)Google Scholar
  10. 10.
    Dereszynski, E.W., Hostetler, J., Fern, A., Dietterich, T.G., Hoang, T., Udarbe, M.: Learning probabilistic behavior models in real-time strategy games. In: Digital Entertainment (2011)Google Scholar
  11. 11.
    Weber, B.G., Mateas, M.: A data mining approach to strategy prediction. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Games, pp. 140–147 (2009)Google Scholar
  12. 12.
    Synnaeve, G., Bessière, P.: A Bayesian model for opening prediction in RTS games with application to StarCraft. In: Proceedings of 2011 IEEE Conference on Computational Intelligence and Games, pp. 281–288 (2011)Google Scholar
  13. 13.
    Wang, K., Shang, W.: Outcome prediction of DOTA2 based on Navïe Bayes classifier. In: Proceedings of 16th IEEE/ACIS International Conference on Computer and Information Science, pp. 591–593 (2017)Google Scholar
  14. 14.
    Cleghern, Z., Lahiri, S., Özaltin, O.Y., Roberts, D.L.: Predicting future states in DOTA 2 using value-split models of time series attribute data. In: Proceedings of the International Conference on the Foundations of Digital Games, pp. 5:1–5:10 (2017)Google Scholar
  15. 15.
    Yang, P., Harrison, B.E., Roberts, D.L.: Identifying patterns in combat that are predictive of success in MOBA games. In: Proceedings of the 9th International Conference on the Foundations of Digital Games (2014)Google Scholar
  16. 16.
    Park, Y.J., Kim, H.S., Kim, D., Lee, H., Kim, S.B., Kang, P.: A deep learning-based sports player evaluation model based on game statistics and news articles. Knowl.-Based Syst. 138, 15–26 (2017)CrossRefGoogle Scholar
  17. 17.
    Leibfried, F., Kushman, N., Hofmann, K.: A deep learning approach for joint video frame and reward prediction in Atari games. CoRR abs/1611.07078 (2016)Google Scholar
  18. 18.
    Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.P.: Action-conditional video prediction using deep networks in Atari games. In: Proceedings of Annual Conference on Neural Information Processing Systems 2015, pp. 2863–2871 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Xuan Lan
    • 1
  • Lei Duan
    • 1
  • Wen Chen
    • 1
  • Ruiqi Qin
    • 1
  • Timo Nummenmaa
    • 2
  • Jyrki Nummenmaa
    • 2
  1. 1.School of Computer ScienceSichuan UniversityChengduChina
  2. 2.Faculty of Natural SciencesUniversity of TampereTampereFinland

Personalised recommendations