Advertisement

Predicting Winning Team and Probabilistic Ratings in “Dota 2” and “Counter-Strike: Global Offensive” Video Games

  • Ilya MakarovEmail author
  • Dmitry Savostyanov
  • Boris Litvyakov
  • Dmitry I. Ignatov
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10716)

Abstract

In this paper, we present novel winning team predicting models and compare the accuracy of the obtained prediction with TrueSkill model of ranking individual players impact based on their impact in team victory for the two most popular online games: “Dota 2” and “Counter-Strike: Global Offensive”. In both cases, we present game analytics for predicting winning team based on game statistics and TrueSkill.

Keywords

Game analytics Rating systems TrueSkill Machine learning Data mining Counter-Strike Dota 2 

Notes

Acknowledgments

The work was supported by the Russian Science Foundation under grant 17-11-01294 and performed at National Research University Higher School of Economics, Russia. We would like to thank Alexander Semenov and Petr Romov for their piece of advice.

References

  1. 1.
    Taylor, T.: Raising the Stakes: E-sports and the Professionalization of Computer Gaming. MIT Press, New York (2012)Google Scholar
  2. 2.
    Powered by Steam: Steamcharts. An ongoing analysis of steam’s concurrent players (2017). http://steamcharts.com/. Accessed 09 May 2017
  3. 3.
    Kaytoue, M., et al.: Watch me playing, i am a professional: a first study on video game live streaming. In: Proceedings of the 21st International Conference on WWW, NY, USA, pp. 1181–1188. ACM (2012)Google Scholar
  4. 4.
    Wagner, M.G.: On the scientific relevance of eSports. In: International Conference on Internet Computing, pp. 437–442 (2006)Google Scholar
  5. 5.
    Luckner, S., Schröder, J., Slamka, C.: On the forecast accuracy of sports prediction markets. In: Gimpel, H., Jennings, N.R., Kersten, G.E., Ockenfels, A., Weinhardt, C. (eds.) Negotiation, Auctions, and Market Engineering. LNBIP, vol. 2, pp. 227–234. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-77554-6_17 CrossRefGoogle Scholar
  6. 6.
    Tsai, M.: Fantasy (e)Sports: the future prospect of fantasy sports betting amongst organized multiplayer video game competitions. UNLV Gaming LJ 6, 393 (2015)Google Scholar
  7. 7.
    Zhang, L., et al.: A factor-based model for context-sensitive skill rating systems. In: 2010 22nd IEEE International Symposium on TAI, vol. 2, pp. 249–255 (2010)Google Scholar
  8. 8.
    Coulom, R.: Whole-history rating: a Bayesian rating system for players of time-varying strength. In: van den Herik, H.J., Xu, X., Ma, Z., Winands, M.H.M. (eds.) CG 2008. LNCS, vol. 5131, pp. 113–124. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-87608-3_11 CrossRefGoogle Scholar
  9. 9.
    Dick, M., Wellnitz, O., Wolf, L.: Analysis of factors affecting players’ performance and perception in multiplayer games. In: Proceedings of 4th ACM SIGCOMM IW on Network and System Support for Games, NY, USA, pp. 1–7. ACM (2005)Google Scholar
  10. 10.
    Wright, T., Boria, E., Breidenbach, P.: Creative player actions in FPS online video games: playing counter-strike. Game Stud. 2(2), 103–123 (2002)Google Scholar
  11. 11.
    Rioult, F., Métivier, J.P., Helleu, B., Scelles, N., Durand, C.: Mining tracks of competitive video games. AASRI Procedia 8, 82–87 (2014)CrossRefGoogle Scholar
  12. 12.
    Hladky, S., Bulitko, V.: An evaluation of models for predicting opponent positions in first-person shooter video games. In: 2008 IEEE International Symposium on CIG, pp. 39–46 (2008)Google Scholar
  13. 13.
    Bird, A.M.: Development of a model for predicting team performance. Am. Alliance Health Phys. Educ. Recreat. 48(1), 24–32 (1977)CrossRefGoogle Scholar
  14. 14.
    Drachen, A., et al.: Skill-based differences in spatio-temporal team behaviour in defence of the ancients 2 (dota 2). In: 2014 IEEE GME, pp. 1–8 (2014)Google Scholar
  15. 15.
    Pobiedina, N., et al.: On successful team formation: Statistical analysis of a multiplayer online game. In: 2013 IEEE 15th International Conference on Business Informatics, pp. 55–62 (2013)Google Scholar
  16. 16.
    Yang, P., Roberts, D.L.: Knowledge discovery for characterizing team success or failure in (A)RTS games. In: 2013 IEEE International Conference on CIG, pp. 1–8, August 2013Google Scholar
  17. 17.
    Wu, M., Xiong, S., Iida, H.: Fairness mechanism in multiplayer online battle arena games. In: Proceedings of 3rd International Conference on SAI (ICSAI), pp. 387–392, November 2016Google Scholar
  18. 18.
    Myślak, M., Deja, D.: Developing game-structure sensitive matchmaking system for massive-multiplayer online games. In: Aiello, L.M., McFarland, D. (eds.) SocInfo 2014. LNCS, vol. 8852, pp. 200–208. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-15168-7_25 Google Scholar
  19. 19.
    Elo, A.: The Rating of Chessplayers, Past and Present. Arco Pub., New York (1978)Google Scholar
  20. 20.
    Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika 39(3/4), 324–345 (1952)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Wu, T.F., Lin, C.J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. J. Mach. Learn. Res. 5, 975–1005 (2004)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Huang, T.K., et al.: Generalized Bradley-Terry models and multi-class probability estimates. J. Mach. Learn. Res. 7, 85–115 (2006)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Fujimoto, Y., Hino, H., Murata, N.: An estimation of generalized Bradley-Terry models based on the em algorithm. Neural Comput. 23(6), 1623–1659 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Matsumoto, I., et al.: Online density estimation of Bradley-Terry models. In: Proceedings of International Conference on Learning Theory, Paris, France, pp. 1343–1359. PMLR (2015)Google Scholar
  25. 25.
    Király, F.J., Qian, Z.: Modelling Competitive Sports: Bradley-Terry-Elo Models for Supervised and On-Line Learning of Paired Competition Outcomes. arXiv preprint arXiv:1701.08055 (2017)
  26. 26.
    Glickman, M.E.: The Qlicko System. Boston University, Boston (1995)Google Scholar
  27. 27.
    Glickman, M.E.: Example of the Qlicko-2 System. Boston University, Boston (2012)Google Scholar
  28. 28.
    Glickman, M.E., Hennessy, J., Bent, A.: A comparison of rating systems for competitive women’s beach volleyball. http://www.glicko.net/
  29. 29.
    Herbrich, R., Minka, T., Graepel, T.: Trueskill™: a Bayesian skill rating system. In: Proceedings of the 19th International Conference on NIPS, MA, USA, pp. 569–576. MIT Press (2006)Google Scholar
  30. 30.
    Graepel, T., Herbrich, R.: Ranking and matchmaking. Game Dev. Mag. 25, 34 (2006)Google Scholar
  31. 31.
    Dangauthier, P., Herbrich, R., Minka, T., Graepel, T., et al.: Trueskill through time: revisiting the history of chess. In: NIPS, pp. 337–344 (2007)Google Scholar
  32. 32.
    Huang, J., et al.: Mastering the art of war: how patterns of gameplay influence skill in halo. In: Proceedings of the SIGCHI International Conference, NY, USA, pp. 695–704. ACM (2013)Google Scholar
  33. 33.
    Wikipedia: Fide world rankings - wikipedia, the free encyclopedia (2017). https://en.wikipedia.org/w/index.php?title=FIDE_World_Rankings&oldid=776755738. Accessed 5 May 2017
  34. 34.
    Moser, J.: Computing your skill (2010). http://www.moserware.com/2010/03/computing-your-skill.html. Accessed 9 May 2017
  35. 35.
    Nikolenko, S., Sirotkin, A.: A new Bayesian rating system for team competitions. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 601–608 (2011)Google Scholar
  36. 36.
    Nikolenko, S.I., Sirotkin, A.V.: Extensions of the trueskilltm rating system. In: Proceedings of the 9th International Conference on AFSSC, pp. 151–160. Citeseer (2010)Google Scholar
  37. 37.
    Bishop, C.M.: Pattern recognition. Mach. Learn. 128, 1–58 (2006)Google Scholar
  38. 38.
    Nikolenko, S.I., Serdyuk, D.V., Sirotkin, A.V.: Bayesian rating systems with additional information on tournament results. Trudy SPIIRAN 22, 189–204 (2012)Google Scholar
  39. 39.
    Nikolenko, S.: A probabilistic rating system for team competitions with individual contributions. In: Khachay, M.Y., Konstantinova, N., Panchenko, A., Ignatov, D.I., Labunets, V.G. (eds.) AIST 2015. CCIS, vol. 542, pp. 3–13. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-26123-2_1 CrossRefGoogle Scholar
  40. 40.
    Buckley, D., Chen, K., Knowles, J.: Rapid skill capture in a first-person shooter. IEEE Trans. Comput. Intell. AI Games 9(1), 63–75 (2017)CrossRefGoogle Scholar
  41. 41.
    Menke, J.E., Martinez, T.R.: A Bradley-Terry artificial neural network model for individual ratings in group competitions. Neural Comput Appl. 17(2), 175–186 (2008)CrossRefGoogle Scholar
  42. 42.
    Tarlow, D., Graepel, T., Minka, T.: Knowing what we don’t know in NCAA football ratings: understanding and using structured uncertainty. In: Proceedings of the 2014 MIT Sloan Sports Analytics Conference (SSAC 2014), pp. 1–8. Citeseer (2014)Google Scholar
  43. 43.
    Lee, J.-S.: TrueSkill-Based pairwise coupling for multi-class classification. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012. LNCS, vol. 7553, pp. 213–220. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33266-1_27 CrossRefGoogle Scholar
  44. 44.
    Naik, N., et al.: Streetscore-predicting the perceived safety of one million streetscapes. In: Proceedings of the IEEE International Conference on CVPR Workshops, pp. 779–785 (2014)Google Scholar
  45. 45.
    Graepel, T., et al.: Web-scale bayesian click-through rate prediction for sponsored search advertising in microsoft’s bing search engine. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 13–20 (2010)Google Scholar
  46. 46.
    Hamilton, S.: Pythonskills: implementation of the trueskill, glicko and elo ranking algorithms (2012)Google Scholar
  47. 47.
    Lee, H.: Python implementation of trueskill: the video game rating system (2013)Google Scholar
  48. 48.
    Shim, K.J., et al.: An exploratory study of player and team performance in multiplayer first-person-shooter games. In: 2011 IEEE 3rd International Conference on Privacy, Security, Risk and Trust and 3rd International Conference on Social Computing, pp. 617–620, October 2011Google Scholar
  49. 49.
    DeLong, C., Pathak, N., Erickson, K., Perrino, E., Shim, K., Srivastava, J.: TeamSkill: modeling team chemistry in online multi-player games. In: Huang, J.Z., Cao, L., Srivastava, J. (eds.) PAKDD 2011. LNCS (LNAI), vol. 6635, pp. 519–531. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-20847-8_43 CrossRefGoogle Scholar
  50. 50.
    DeLong, C., Srivastava, J.: TeamSkill evolved: mixed classification schemes for team-based multi-player games. In: Tan, P.-N., Chawla, S., Ho, C.K., Bailey, J. (eds.) PAKDD 2012. LNCS (LNAI), vol. 7301, pp. 26–37. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-30217-6_3 CrossRefGoogle Scholar
  51. 51.
    DeLong, C., Terveen, L., Srivastava, J.: TeamSkill and the NBA: applying lessons from virtual worlds to the real-world. In: Proceedings of the 2013 IEEE/ACM International Conference on Advances in SNA and Mining, NY, USA, pp. 156–161. ACM (2013)Google Scholar
  52. 52.
    McDonald, T.: A beginner’s guide to dota 2: Part one - the basics (2013). https://www.pcinvasion.com/a-beginners-guide-to-dota-2-part-one-the-basics. Accessed 25 July 2013
  53. 53.
    Conley, K., Perry, D.: How does he saw me? A recommendation engine for picking heroes in dota 2. Np, nd Web 7 (2013)Google Scholar
  54. 54.
    Semenov, A., Romov, P., Korolev, S., Yashkov, D., Neklyudov, K.: Performance of machine learning algorithms in predicting game outcome from drafts in dota 2. In: Ignatov, D.I., Khachay, M.Y., Labunets, V.G., Loukachevitch, N., Nikolenko, S.I., Panchenko, A., Savchenko, A.V., Vorontsov, K. (eds.) AIST 2016. CCIS, vol. 661, pp. 26–37. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-52920-2_3 CrossRefGoogle Scholar
  55. 55.
    Agarwala, A., Pearce, M.: Learning dota 2 team compositions. Technical report, Stanford University (2014)Google Scholar
  56. 56.
    Song, K., Zhang, T., Ma, C.: Predicting the winning side of dota2. Technical report, Stanford University (2015)Google Scholar
  57. 57.
    Yang, Y., Qin, T., Lei, Y.H.: Real-time esports match result prediction. arXiv preprint arXiv:1701.03162 (2016)
  58. 58.
    Johansson, F., Wikström, J.: Result prediction by mining replays in dota 2 (2015)Google Scholar
  59. 59.
    Inkarnate: Dota 1-to-5 system (2012). http://www.liquiddota.com/forum/dota-2-strategy/454943-dota-1-to-5-system. Accessed 05 Sep 2011
  60. 60.
    Eggert, C., Herrlich, M., Smeddinck, J., Malaka, R.: Classification of player roles in the team-based multi-player game dota 2. In: Chorianopoulos, K., Divitini, M., Hauge, J.B., Jaccheri, L., Malaka, R. (eds.) ICEC 2015. LNCS, vol. 9353, pp. 112–125. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24589-8_9 CrossRefGoogle Scholar
  61. 61.
    Pobiedina, N., et al.: Ranking factors of team success. In: Proceedings of the 22 International Confetence on World Wide Web, NY, USA, pp. 1185–1194. ACM (2013)Google Scholar
  62. 62.
    Powered by Steam: Stats from professional dota 2 matches (2017). https://www.opendota.com/explorer. Accessed 01 May 2017
  63. 63.
    DotaBuff: Kiev major: team eg vs. team og (2017). https://www.dotabuff.com/matches/3148721353. Accessed 16 May 2017
  64. 64.
    StatsHelix: Cs:go demos parser by statshelix (2014). https://github.com/StatsHelix/demoinfo. Accessed 9 May 2017
  65. 65.
    Valve: csgo-demoinfo (2014). https://github.com/ValveSoftware/csgo-demoinfo/tree/master/demoinfogo. Accessed 5 May 2017
  66. 66.
    HLTV.org: Hltv.org demos section (2017). hltv.org/?pageid=28. Accessed 9 May 2017

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.National Research University Higher School of EconomicsMoscowRussia

Personalised recommendations