Abstract
The domain of knowledge contained in Multiplayer Online Battle Arena (MOBA) is quite complex, which is of great research value. With the rapid development of E-sports, the impact of data analysis on MOBA games is increasing. For example, data mining and deep learning methods can be used to guide players and develop appropriate strategies to win games. This paper proposes a novel MOBA game analysis system. The system includes three individual modules, namely lineup recommendation, real-time win rate prediction, and trend forecasting. The lineup module is implemented using NSGA-II algorithm to recommend hero combinations according to the enemy lineup. Win rate module is a neural network for predicting the quantitative advantage between teams. Trend module is a sequence-to-sequence model that forecasts the future team gold and exp. Finally, the system is applied to Dota 2, one of the most popular MOBA games. Experiments on a large number of professional match replays show that the system works well on arbitrary matches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Summerville, A., Cook, M., Steenhuisen, B.: Draft-analysis of the ancients: predicting draft picks in dota 2 using machine learning. In: Twelfth Artificial Intelligence and Interactive Digital Entertainment Conference (2016)
Zhang, L., et al.: Improved dota 2 lineup recommendation model based on a bidirectional LSTM. Tsinghua Sci. Technol. 25(6), 712–720 (2020)
Chen, Z., et al.: The art of drafting: a team-oriented hero recommendation system for multiplayer online battle arena games. In: Proceedings of the 12th ACM Conference on Recommender Systems, pp. 200–208 (2018)
Yang, Y., Qin, T., Lei, Y.H.: Real-time esports match result prediction. arXiv preprint arXiv:1701.03162 (2016)
Yu, L., et al.: Moba-slice: a time slice based evaluation framework of relative advantage between teams in moba games. In: Workshop on Computer Games, pp. 23–40. Springer, Cham (2018)
Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)
Wu, B.: Hierarchical macro strategy model for moba game AI. Proc. AAAI Conf. Artif. Intell. 33(01), 1206–1213 (2019)
Ye, D., et al.: Mastering complex control in MOBA games with deep reinforcement learning. Proc. AAAI Conf. Artif. Intell. 34(04), 6672–6679 (2020)
Wang, N., et al.: Outcome prediction of dota 2 using machine learning methods. In: Proceedings of 2018 International Conference on Mathematics and Artificial Intelligence, pp. 61–67 (2018)
Deb, K., et al.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Acknowledgment
.This work is supported by the National Natural Science Foundation of China (62072084, 62072086, 62172082), the National Defense Basic Scientific Research Program of China (JCKY2018205C012), and the Fundamental Research Funds for the Central Universities (N2116008).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, K. et al. (2021). MOBA Game Analysis System Based on Neural Networks. In: Zhang, W., Zou, L., Maamar, Z., Chen, L. (eds) Web Information Systems Engineering – WISE 2021. WISE 2021. Lecture Notes in Computer Science(), vol 13081. Springer, Cham. https://doi.org/10.1007/978-3-030-91560-5_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-91560-5_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91559-9
Online ISBN: 978-3-030-91560-5
eBook Packages: Computer ScienceComputer Science (R0)