Interpretable Real-Time Win Prediction for Honor of Kings, a Popular Mobile MOBA Esport

With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), many research efforts have been devoted to automatically predicting the game results (win predictions). While this task has great potential in various applications such as esports live streaming and game commentator AI systems, previous studies suffer from two major limitations: 1) insufficient real-time input features and high-quality training data; 2) non-interpretable inference processes of the black-box prediction models. To mitigate these issues, we collect and release a large-scale dataset that contains real-time game records with rich input features of the popular MOBA game Honor of Kings. For interpretable predictions, we propose a Two-Stage Spatial-Temporal Network (TSSTN) that can not only provide accurate real-time win predictions but also attribute the ultimate prediction results to the contributions of different features for interpretability. Experiment results and applications in real-world live streaming scenarios show that the proposed TSSTN model is effective both in prediction accuracy and interpretability.

[1]  Dursun Delen,et al.  A comparative analysis of data mining methods in predicting NCAA bowl outcomes , 2012 .

[2]  Kaushik Kalyanaraman,et al.  To win or not to win ? A prediction model to determine the outcome of a DotA 2 match , 2015 .

[3]  D. Perry,et al.  How Does He Saw Me ? A Recommendation Engine for Picking Heroes in Dota 2 , 2013 .

[4]  Victoria J. Hodge,et al.  Time to Die: Death Prediction in Dota 2 using Deep Learning , 2019, 2019 IEEE Conference on Games (CoG).

[5]  Sam Devlin,et al.  Win Prediction in Multiplayer Esports: Live Professional Match Prediction , 2021, IEEE Transactions on Games.

[6]  Yifan Yang,et al.  Real-time eSports Match Result Prediction , 2016, ArXiv.

[7]  César Soto-Valero,et al.  Predicting Win-Loss outcomes in MLB regular season games - A comparative study using data mining methods , 2016, Int. J. Comput. Sci. Sport.

[8]  Tianyi Zhang,et al.  Predicting the winning side of DotA 2 , 2015 .

[9]  Zhengxing Chen,et al.  Modeling Game Avatar Synergy and Opposition through Embedding in Multiplayer Online Battle Arena Games , 2018, ArXiv.

[10]  Peter Romov,et al.  Performance of Machine Learning Algorithms in Predicting Game Outcome from Drafts in Dota 2 , 2016, AIST.

[11]  Alison Watkins,et al.  A Data Snapshot Approach for Making Real-Time Predictions in Basketball , 2018, Big Data.

[12]  Dmitry I. Ignatov,et al.  Predicting Winning Team and Probabilistic Ratings in "Dota 2" and "Counter-Strike: Global Offensive" Video Games , 2017, AIST.

[13]  Kai Song,et al.  Making real-time predictions for NBA basketball games by combining the historical data and bookmaker’s betting line , 2020 .

[14]  Carson Kai-Sang Leung,et al.  Sports Data Mining: Predicting Results for the College Football Games , 2014, KES.

[15]  Hao Wu,et al.  Mastering Complex Control in MOBA Games with Deep Reinforcement Learning , 2019, AAAI.

[16]  Han Liu,et al.  Feedback-Based Tree Search for Reinforcement Learning , 2018, ICML.

[17]  Min Chen,et al.  Hierarchical Reinforcement Learning for Multi-agent MOBA Game , 2019, ArXiv.

[18]  Alison Watkins,et al.  Predicting the point spread in professional basketball in real time: a data snapshot approach , 2019, Journal of Business Analytics.

[19]  Nicholas Kinkade,et al.  DOTA 2 Win Prediction , 2015 .

[20]  Sam Devlin,et al.  Win Prediction in Esports: Mixed-Rank Match Prediction in Multi-player Online Battle Arena Games , 2017, ArXiv.

[21]  Bo Li,et al.  TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game , 2018, ArXiv.

[22]  Florian Block,et al.  Role Identification for Accurate Analysis in Dota 2 , 2019, AIIDE.

[23]  Lin Li,et al.  Outcome prediction of DOTA2 using machine learning methods , 2018, ICMAI.