Mobile Legends Win Rate Prediction and Team Recommendation Using Switched Hero Roles

Pir Hamid Ali Qureshi; Areej Fatemah Meghji; Rabeea Jaffari

Authors

Pir Hamid Ali Qureshi Department of Software Engineering, Mehran University of Engineering and Technology, Jamshoro, Pakistan.
Areej Fatemah Meghji Department of Software Engineering, Mehran University of Engineering and Technology, Jamshoro, Pakistan.
Rabeea Jaffari Department of Software Engineering, Mehran University of Engineering and Technology, Jamshoro, Pakistan.

Keywords:

Machine learning, recommendation, feature selection, regression, mobile gaming

Abstract

Mobile Legends Bang Bang (MLBB) falls under the category of a Multi Online Battle Arena game. Games like MLBB require players to have strong skills and strategic gameplay; team composition is an important factor influencing the chances of winning the game. Although there is data currently available for MLBB, two aspects of this game that remain unexplored include: i) win rate prediction using nontraditional roles in heroes, and ii) team composition with switched hero roles. While picking heroes for each team, a team chooses heroes that they know perform well using a traditional role. However, nothing has been mentioned as to what happens when heroes are selected using a nontraditional role. This research aims to address this question by predicting the win rate of heroes with switched roles. This unpredictability will lead to the formation of a team that can have a significant advantage over the enemy team thus leading to victory. The dataset for this study was formulated by focusing on 67 heroes in the game. The win rates were generated with real-time simulations where the ally team members remained unchanged to avoid biased results. Using two model-building approaches, win rate predictions were made using 12 regression algorithms under 5 feature selection settings. The research has shown that LightGBM with AdaBoost as the base estimator provides better results and was used to formulate 5 teams. A recommendation system was designed to optimize team composition from the win rate prediction analysis. To validate the results, we simulated 50 matches with each team, with ally team players remaining the same to avoid biased results. This resulted in a 94% win rate with 47 wins and 3 losses out of a total of 50 matches.

References

A. Turner, “How Many Smartphones Are in the World?,” BankMyCell, Aug. 2023. [Online]. Available: https://www.bankmycell.com/blog/how-many-phones-are-in-the-world. [Accessed: Oct. 1, 2023].

J. Degenhard, “Number of smartphone users worldwide 2013-2028,” Statista, Aug. 14, 2023. [Online]. Available: https://www.statista.com/forecasts/1143723/smartphone-users-in-the-world. [Accessed: Oct. 11, 2023].

Statista, “Mobile Games - Worldwide | Statista Market Forecast,” Statista, 2023. [Online]. Available: https://www.statista.com/outlook/dmo/digital-media/video-games/mobile-games/worldwide. [Accessed: Oct. 12, 2024].

S. K. Lee, S. J. Hong, and S. I. Yang, “Predicting game outcome in Multiplayer Online Battle Arena Games,” in 2020 International Conference on Information and Communication Technology Convergence (ICTC), 2020, doi: 10.1109/ICTC49870.2020.9289254.

M. Lobanova, “What Makes Moba Games So Successful?,” Hackernoon, Nov. 11, 2022. [Online]. Available: https://hackernoon.com/what-makes-moba-games-so-successful. [Accessed: Oct. 1, 2024].

UniPin Blog, “Explanation of the Lane in Mobile Legends,” https://blog.unipin.com/en/explanation-of-the-lane-in-mobile-legends/ [Accessed: Jan. 27, 2025]

D. A. Team, “Unveiling the Mysteries of AI Supervised Learning: A comprehensive overview,” Deep AI — Leading Generative AI-powered Solutions for Business, Jul. 14, 2024. Accessed: Oct 04, 2024 [Online]. Available: https://deepai.tn/glossary/supervised-learning-ai-explained/

A. F. Meghji, N. A. Mahoto, Y. Asiri, H. Alshahrani, A. Sulaiman, and A. Shaikh, “Early detection of student degree-level academic performance using educational data mining,” PeerJ Computer Science, vol. 9, pp. e1294, 2023, doi: 10.7717/peerj-cs.1294.

K. Arık, “Machine learning models on MOBA Gaming: League of Legends Winner Prediction,” Acta Infologica, vol. 7, no. 1, pp. 139–151, 2023, doi: 10.26650/acin.1180583.

T. D. Do, S. I. Wang, D. S. Yu, M. G. McMillian, and R. P. McMahan, “Using machine learning to predict game outcomes based on player-champion experience in League of Legends,” in Proc. 16th Int. Conf. Foundations of Digital Games (FDG), 2021, doi: 10.1145/3472538.3472579.

A. S. Chan, F. Fachrizal, and A. R. Lubis, “Outcome prediction using naïve Bayes algorithm in the selection of role hero mobile legend,” J. Phys.: Conf. Ser., vol. 1566, no. 1, p. 012041, 2020, doi: 10.1088/1742-6596/1566/1/012041.

R. Ani, V. Harikumar, A. K. Devan, and O. S. Deepa, “Victory prediction in league of legends using feature selection and ensemble methods,” in Proc. 2019 Int. Conf. Intell. Comput. Control Syst. (ICCS), 2019, doi: 10.1109/iccs45141.2019.9065758.

D. Mahendra, “Decision Tree Application for Choosing Champions in League of Legends,” no. 13518003, Dec. 2019. Accessed: Oct. 01, 2023. [Online]. Available: https://informatika.stei.itb.ac.id/~rinaldi.munir/Matdis/2019-2020/Makalah2019/13518003.pdf.

M. Pengmatchaya and J. Natwichai, “Identifying player skill of dota 2 using machine learning pipeline,” Discover Artificial Intelligence, vol. 4, no. 1, May 2024, doi: 10.1007/s44163-024-00139-y.

Chen, Z., Nguyen, T. H. D., Xu, Y., Amato, C., Cooper, S., Sun, Y., & El-Nasr, M. S. (2018, September). “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), doi: 10.1145/3240323.3240345.

S.-J. Hong, S.-K. Lee, and S.-I. Yang, “Champion recommendation system of League of Legends,” 2020 International Conference on Information and Communication Technology Convergence (ICTC), vol. 1215, pp. 1252–1254, Oct. 2020. doi:10.1109/ictc49870.2020.9289546

C. E. M. Almeida, R. C. M. Correia, D. M. Eler, C. Olivete-Jr, R. E. Garcia, L. C. Scabora, and G. Spadon, “Prediction of Winners in MOBA Games,” in Proceedings of the Department of Mathematics and Computing, Universidade Estadual Paulista (UNESP), São Paulo, Brazil, 2024.

I. Porokhnenko, P. Polezhaev, and A. Shukhman, “Machine Learning Approaches to Choose Heroes in Dota 2,” in Proc. 24th Conf. FRUCT Assoc., 2024, pp. 346-350.

J. B. S. Junior and C. E. C. Campelo, “League of Legends: Real-Time Result Prediction,” in Proc. of the IEEE, 2024, pp. 1-10.

N. Tangniyom and P. Boonma, “A Study on Using Machine Learning to Predict Winner in Multiplayer Online Battle Arena (MOBA) Game,” ASEAN Journal of Scientific and Technological Reports, vol. 27, no. 5, pp. e252289, 2024, doi: 10.55164/ajstr.v27i5.252289.

Y. S. Kim, P. Prabhakar, and A. Dutta, “Champion Recommender System For League of Legends,” University of Washington, Preprint.

L. Hanke and L. Chaimowicz, “A Recommender System for Hero Line-Ups in MOBA Games,” in Proc. Thirteenth AAAI Conf. Artificial Intelligence and Interactive Digital Entertainment (AIIDE-17), 2017, pp. 43-49.

A. Sapienza, P. Goyal, and E. Ferrara, “Deep Neural Networks for Optimal Team Composition,” Frontiers in Big Data, vol. 2, no. 14, pp. 1-13, Jun. 2019, doi: 10.3389/fdata.2019.00014.

Elavarasan, D., Vincent PM, D. R., Srinivasan, K., & Chang, C. Y. (2020). A hybrid CFS filter and RF-RFE wrapper-based feature extraction for enhanced agricultural crop yield prediction modeling. Agriculture, 10(9), 400.

Jadhav, P., Patil, D. V., & Gore, D. S. (2020, May). A comparative study of linear regression and regression tree. In 2nd International Conference on Communication & Information Processing (ICCIP).

James, Gareth, et al. "Linear regression." An introduction to statistical learning: With applications in python. Cham: Springer International Publishing, 2023. 69-134.

R. W. Hoerl, “Ridge Regression: A Historical Context,” Technometrics, vol. 62, no. 4, pp. 420-425, Oct. 2020, doi: 10.1080/00401706.2020.1742207.

L. Zhang, X. Wei, J. Lu, and J. Pan, “Lasso Regression: From Explanation to Prediction,” Advances in Psychological Science, vol. 28, no. 10, pp. 1777-1788, 2020. doi: 10.3724/SP.J.1042.2020.01777.

Jayanth, S. B., Anthony, A., Abhilasha, G., Shaik, N., & Srinivasa, G. (2018). A team recommendation system and outcome prediction for the game of cricket. Journal of Sports Analytics, 4(4), 263-273.

T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785-794, doi: 10.1145/2939672.2939785.

A. Natekin and A. Knoll, "Gradient boosting machines, a tutorial," *Frontiers in Neurorobotics*, vol. 7, art. no. 21, 2013. DOI: [10.3389/fneur.2013.00021](https://doi.org/10.3389/fneur.2013.00021).

J. K. Jaiswal and R. Samikannu, "Application of Random Forest Algorithm on Feature Subset Selection and Classification and Regression," 2017 World Congress on Computing and Communication Technologies (WCCCT), Tiruchirappalli, India, 2017, pp. 65-68, doi: 10.1109/WCCCT.2016.25.

Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937-1967.