MOBA Oyunlarında Makine Öğrenimi Teknikleri: League of Legends Kazanan Tahmini

Abstract

Eğlence endüstrisi, telekomünikasyon hizmetleri, televizyon, müzik, video oyunları ve canlı konserler gibi işlerle uğraşan alışılmadık derecede geniş bir şirket yelpazesini içerir. Oyun, son on yılda eğlence sektöründe gelir artışı ivmesi elde etmiştir. Bu ivme oyun sektörünü eğlence endüstrisinin en popular alanlarından biri haline getirmiştir. Profesyonel oyuncularla resmi ligler kurulmuş ve e-spor kavramı yaygın hale gelmeye başlamıştır. Çevrimiçi oyun türlerinden olan MMO (Massive Multiplayer Online) oyunların bir türevi olarak karşımıza çıkan MOBA (Multiplayer Online Battle Arena) internet üzerinde genellikle 5 kişilik 2 takımla bir harita üzerinde belirli yapıları domine ederek rakibin üssünü yok etme hedefiyle oynanan oyunlara verilen isimdir. LoL (League of Legends) bir MOBA oyunudur. Çevrimiçi video oyunlarında kazananların tahmini, makine öğrenmesi tabanlı tahmin modelleri için önemli bir uygulama haline gelmiştir. Araştırmanın hedefi LoL oyuncu metrikleriyle maç kazanma tahminin makine öğrenmesi yöntemleriyle sınıflandırma tahminidir. Önemli performans ölçütleri ve bunların her bir oyun modeli üzerindeki etkisi de analiz edildi. Sonuçlar, League of Legends oyununda kazanan tahmininin mümkün olduğunu göstermektedir. LightGBM (0.97), Lojistik regresyon (0,96), SVM ve GBC (0.95) başarım oranı ile öne çıkan algoritmalardır. Çalışmanın oyun alanında makine öğrenmesiyle sınıflandırma çalışmalarına katkı sağlayacağı düşünülmektedir.

Keywords

• Makine Öğrenmesi
• Sınıflandırma
• Oyun
• League of Legends
• MOBA

Machine Learning Models on MOBA Gaming: League of Legends Winner Prediction

Abstract

The entertainment industry includes companies engaged in telecommunications services, television, music streaming, video games, and live events. Gaming has gained momentum in revenue growth in the entertainment industry over the past decade. This momentum has made the gaming industry one of the most popular areas of the entertainment industry. Official leagues have been teamed up with professional players, and the concept of e-sports has become widespread. MOBA (Multiplayer Online Battle Arena), which is a derivative of MMO (massively multiplayer online) games, is the name given to the games played on the Internet in which players destroy the opponent's base by dominating specific objectives on a map, usually with two teams of five players each. LoL (League of Legends) is one of the most popular MOBA games. Predicting winners in online games has become an essential application for machine learning models. This research aims to predict classification with machine learning methods of match winner with LoL player metrics. Key performance metrics and their impact on each game model were analyzed. The results show that winner prediction is possible in League of Legends, also, LightGBM (0.97), Logistic Regression (0.96), SVM and GBC (Gradient Boosting Classifier) (0.95) are outperformed with a high accuracy ratio. This paper will contribute to the classification research on topic of gaming with machine learning.

Keywords

• Gaming
• Classification
• Machine Learning
• League of Legends
• Moba

References

1. Almeida, C. E. M., Correia, R. C. M., Eler, D. M., Olivete-Jr, C., Garci, R. E., Scabora, L. C., & Spadon, G. (2017). Prediction of winners in MOBA games. google scholar
2. 201712th Iberian Conference on Information Systems and Technologies (CISTI), 1-6. https://doi.org/10.23919/CISTI.2017.7975774 google scholar
3. Alpaydin, E. (2020). Introduction to machine learning (Fourth edition). The MIT Press. google scholar
4. Ani, R., Harikumar, V., Devan, A. K., & Deepa, O. S. (2019). Victory prediction in League of Legends using Feature Selection and Ensemble methods. google scholar
5. 2019 International Conference on Intelligent Computing and Control Systems (ICCS), 74-77. https://doi.org/10.1109/ICCS45141.2019.9065758 google scholar
6. Arık, K., Gezer, M., & Tayali, S. T. (2022). Bibliometric Analysis of Scientific Studies Published on Game Customer Churn Analysis Between 2008 and 2022. Journal ofPolitics, 5(1), 21. google scholar
7. Beverly Peders. (2018). Film vs. Video Games From A Screenwriter’s Perspective. https://www.wescreenplay.com/blog/ film-vs-video-games-from-a-screenwriters-perspective/ google scholar
8. Costa, L. M., Mantovani, R. G., Monteiro Souza, F. C., & Xexeo, G. (2021). Feature Analysis to League of Legends Victory Prediction on the Picks and Bans Phase. 2021 IEEE Conference on Games (CoG), 01-05. https://doi.org/10.1109/CoG52621.2021.9619019 google scholar

9. Donovan, T. (2010). Replay: The history of video games. Yellow Ant. google scholar
10. Galehantomo, G. (2015). Platform Comparison Between Games Console, Mobile Games And PC Games. SISFORMA, 2, 23. https://doi.org/10.24167/ sisforma.v2i1.407 google scholar
11. Geron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems (Second edition). O’Reilly Media, Inc. google scholar
12. Han, J., & Kamber, M. (2012). Data mining: Concepts and techniques (3rd ed). Elsevier. google scholar
13. IBM. (2021, August 17). IBM Documentation. https://prod.ibmdocs-production-dal-6099123ce774e592a519d7c33db8265e-0000.us-south.containers. google scholar
14. appdomain.cloud/docs/en/spss-modeler/saas?topic=dm-crisp-help-overview google scholar
15. Justesen, N., Bontrager, P., Togelius, J., & Risi, S. (2019). Deep Learning for Video Game Playing (arXiv:1708.07902). arXiv. https://doi.org/10.48550/ arXiv.1708.07902 google scholar
16. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (n.d.). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 9. Kent, S. L. (2001). The ultimate history of video games: From Pong to Pokemon and beyond: the story behind the craze that touched our lives and changed the world (1st ed). Prima Pub. google scholar
17. Kleinbaum, D. G., & Klein, M. (2010). Introduction to Logistic Regression. In Logistic Regression: A Self-Learning Text (pp. 1-39). Springer. https://doi. org/10.1007/978-1-4419-1742-3_1 google scholar Krzanowski, W. J., & Hand, D. J. (2009). ROC curves for continuous data. Chapman & Hall/CRC. google scholar
18. League ofLegends Live Player Count and Statistics. (2022, July 11). https://activeplayer.io/league-of-legends/ google scholar
19. Lemarechal, C. (2012). Cauchy and the Gradient Method. Documenta Mathematica, 4. google scholar
20. Mason, L., Baxter, J., Bartlett, P. L., & Frean, M. R. (1999). Boosting Algorithms as Gradient Descent. 3, 7. google scholar
21. Michael Donovan. (2014, February 3). The MMO vs. The MOBA. https://www.gamedeveloper.com/disciplines/the-mmo-vs-the-moba google scholar
22. Microsoft. (2022). LightGBM Documentation. https://lightgbm.readthedocs.io/en/v3.3.2/ google scholar
23. Mora-Cantallops, M., & Sicilia, M.-Â. (2018). Player-centric networks in League of Legends. Social Networks, 55, 149-159. https://doi.Org/10.1016/j.socnet.2018.06.002 google scholar
24. Nathan Reiff. (2022). 10 Biggest Entertainment Companies. https://www.investopedia.com/articles/investing/020316/worlds-top-10-entertainment-companies-cmcsa-cbs.asp google scholar
25. Nestor Gilbert. (2022). Number of Gamers Worldwide 2022/2023: Demographics, Statistics, and Predictions. https://financesonline.com/ number-of-gamers-worldwide/ google scholar
26. Nilsson, N. J. (2010). The quest for artificial intelligence: A history of ideas and achievements. Cambridge University Press. google scholar
27. Oracle. (2020). What is Customer Loyalty? https://www.oracle.com/tr/cx/marketing/customer-loyalty/what-is-customer-loyalty/ google scholar
28. Porokhnenko, I., Polezhaev, P., & Shukhman, A. (2019). Machine Learning Approaches to Choose Heroes in Dota 2. 2019 24th Conference of Open Innovations Association (FRUCT), 345-350. https://doi.org/10.23919/FRUCT.2019.8711985 google scholar
29. Robson, J., & Meskin, A. (2016). Video Games as Self-Involving Interactive Fictions. The Journal ofAesthetics and Art Criticism, 74(2), 165-177. google scholar
30. Schreier, J. (2017). Blood, sweat, and pixels: The triumphant, turbulent stories behind how video games are made (First edition). Harper Paperbacks. google scholar
31. Shajihan, N. (2020). Classification of stages ofDiabetic Retinopathy using Deep Learning. https://doi.org/10.13140/RG.2.2.10503.62883 google scholar
32. Simon Kemp. (2022). Digital 2022: Global Overview Report [Analysis]. https://datareportal.com/reports/digital-2022-global-overview-report google scholar
33. Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote Sensing ofEnvironment, 62(1), 77-89. https://doi. org/10.1016/S0034-4257(97)00083-7 google scholar
34. Tim Sevenhuysen. (n.d.). Oracle’s Elixir—LoL Esports Stats. Retrieved September 15, 2022, from https://oracleselixir.com/tools/downloads google scholar
35. William Noble. (2006). What is a support vector machine? | Nature Biotechnology. https://www.nature.com/articles/nbt1206-1565 google scholar
36. Wright, R. E. (1995). Logistic regression. In Reading and understanding multivariate statistics (pp. 217-244). American Psychological Association. google scholar
37. Yang, Z., Pan, Z., Wang, Y., Cai, D., Liu, X., Shi, S., & Huang, S.-L. (2021). Interpretable Real-Time Win Prediction for Honor ofKings, a Popular Mobile MOBA Esport (arXiv:2008.06313). arXiv. https://doi.org/10.48550/arXiv.2008.06313 google scholar