VWPI (Valorant Win Probability Index)
an analytical counterpoint to betting odds
DOI:
https://doi.org/10.5281/zenodo.20076441Keywords:
Betting, Data Science, VWPI, Valorant, XGBoostAbstract
This study proposes the development of a hybrid machine learning model, using the XGBoost and Skellam algorithms, for predicting wins in the esports game Valorant. Given the rise of esports and the viability of data-driven approaches, the research introduces the VWPI (Valorant Win Probability Index) model. The central objective is to establish an indicator to measure the individual contribution of each player, according to their specific role, in calculating the team's probability of winning. The methodology was based on the analysis of data from 1,360 matches, allowing the classifier to estimate the positional value and impact of each team member on the final result. The results demonstrate that the model is able to surpass the probabilities stipulated by bookmakers by detecting performance variables. It is concluded that the VWPI model presents itself as a viable and robust tool for the statistical and computational modeling of scores in competitions.
Downloads
References
AKIBA, T. et al. Optuna: A Next-generation Hyperparameter Optimization Framework. 2019. Disponível em: https://arxiv.org/pdf/1907.10902. Acesso em: 14 dez. 2025.
ALVES DE FREITAS, A. A.; DOS SANTOS, A. Probabilistic model based on the Skellam distribution: application in sports betting. Brazilian Journal of Biometrics, 43(3), e-43773, 2025. Disponível em: https://doi.org/10.28951/bjb.v43i3.773. Acesso em: 14 dez. 2025.
BISHOP, C. Pattern Recognition and Machine Learning. Journal of Electronic Imaging, v. 16, n. 4, p. 049901, 2007. Disponível em: https://www.researchgate.net/publication/221995544_Pattern_Recognition_and_Machine_Learning. Acesso em: 14 dez. 2025
CHEN, T.; GUESTRIN, C. XGBoost: A Scalable Tree Boosting System. In: Proceedings Of The 22nd Acm Sigkdd International Conference On Knowledge Discovery And Data Mining, 2016. Disponível em: https://arxiv.org/pdf/1603.02754. Acesso em: 14 nov. 2025.
FENG, Guanhao; POLSON, Nicholas; XU, Jianeng. The Market for English Premier League (EPL) Odds. Booth School of Business, University of Chicago, [s. l.], p. 1-25, jan. 2017. Disponível em: https://arxiv.org/pdf/1604.03614. Acesso em: 15 nov. 2025.
FLEMING, Owen; SINGH, Tejendra Pratap; YUSUFF, Olanrewaju. The Effect of Online Sports Gambling Laws on Time Use. Preprint 2024. Disponível em: https://d.repec.org/n?u=RePEc:osf:osfxxx:nxg6y. Acesso em: 15 nov. 2025.
GALEKWA, René Manassé; TSHIMULA, J. M.; TAJEUNA, E. G.; KYANDOGHERE, K. A systematic review of machine learning in sports betting: techniques, challenges and future directions. arXiv preprint arXiv:2410.21484, 28 out. 2024. Disponível em: https://arxiv.org/abs/2410.21484. Acesso em: 13 dez. 2025.
GREER, N.; ROCKLOFF, M. J.; RUSSELL, A. M. T.; LOLE, L. Are eSports bettors a new generation of harmed gamblers? A comparison with sports bettors on gambling involvement, problems, and harm. Journal of Behavioral Addictions, v. 10, n. 3, p. 435-446, 2021. DOI: 10.1556/2006.2021.00039. Disponível em: https://akjournals.com/view/journals/2006/10/3/article-p435.xml. Acesso em: 22 out. 2025.
HING, Nerilee. A bad bet for sports fans: the case for ending the “gamblification” of sport audiences. Sport Management Review, v. 26, n. 5, p. 788-812, 2023. DOI: 10.1080/14413523.2023.2260079. Disponível em: https://www.tandfonline.com/doi/full/10.1080/14413523.2023.2260079. Acesso em: 22 out. 2025.
HUTTER, Frank; KOTTHOFF, Lars; VANSCHOREN, Joaquin (Ed.). Automated Machine Learning: Methods, Systems, Challenges. Cham: Springer International Publishing, 2019. Disponível em: https://link.springer.com/book/10.1007/978-3-030-05318-5. Acesso em: 14 dez. 2025.
INMON, W. H. Building the data warehouse. Indianapolis, In: Wiley Pub, 2005.
JIMÉNEZ, V. et al. Sports Betting: an application of neural networks and modern portfolio theory to the English Premier League. Disponível em: https://arxiv.org/abs/2307.13807. Acesso em: 14 dez. 2025
KARLIS, D, NTZOUFRAS, I. Analysis of sports data by using bivariate Poisson models. Journal of the Royal Statistical Society: Series D (The Statistician), v. 52, n. 3, p. 381–393, 2003. Disponível em: http://www2.stat-athens.aueb.gr/~jbn/papers2/08_Karlis_Ntzoufras_2003_RSSD.pdf. Acesso em: 11 dez. 2025
KIM, Hyoun S. et al. A scoping review of the association between loot boxes, eSports, skin betting, and token wagering with gambling and video gaming behaviours. Journal of Behavioral Addictions, v. 12, n. 2, p. 309-351, 2023. DOI: 10.1556/2006.2023.00013. Disponível em: https://pmc.ncbi.nlm.nih.gov/articles/PMC10316162/. Acesso em: 22 out. 2025.
KIM, Hyoun S.; LESLIE, R. Diandra; STEWART, Sherry H.; KING, Daniel L.; DEMETROVICS, Zsolt; ANDRADE, André Luiz Monezi; CHOI, Jung-Seok; TAVARES, Hermano; ALMEIDA, Brittany; HODGINS, David C. A scoping review of the association between loot boxes, eSports, skin betting, and token wagering with gambling and video gaming behaviours. Journal of Behavioral Addictions, v. 12, n. 2, p. 309-351, 2023. DOI: 10.1556/2006.2023.00013. Disponível em: https://pubmed.ncbi.nlm.nih.gov/34419935/. Acesso em: 22 out. 2025.
KIMBALL, Ralph; ROSS, Margy; BECKER, Bob; MUNDY, Joy; THORNTHWAITE, Warren. The Data Warehouse Lifecycle Toolkit. 2. ed., Wiley, 2008. Disponível em: https://www.kimballgroup.com/data-warehouse-business-intelligence-resources/books/data-warehouse-dw-lifecycle-toolkit/. Acesso em: 15 nov. 2025.
LESSMANN, Stefan; SUNG, Ming‑Chien; JOHNSON, Johnnie E.V. Alternative methods of predicting competitive events: An application in horserace betting markets. International Journal of Forecasting, v. 26, n. 3, p. 518–536, 2010. Disponível em: 10.1016/j.ijforecast.2009.12.013. Acesso em: 13 out. 2025.
MANDADAPU, Purnachandra. The Evolution of Football Betting: A Machine Learning Approach to Match Outcome Forecasting and Bookmaker Odds Estimation. arXiv preprint arXiv:2403.16282, 2024. Disponível em: https://arxiv.org/abs/2403.16282. Acesso em: 13 out. 2025.
MANGAT, Harshdeep S.; GRIFFITHS, Mark D.; YU, Shu M.; FELVINCZI, Katalin; NGETICH, Ronald K.; DEMETROVICS, Zsolt; CZAKÓ, Andrea. Understanding Esports-related Betting and Gambling: A Systematic Review of the Literature. Journal of Gambling Studies, v. 40, n. 2, p. 893–914, 2024. Disponível em: https://doi.org/10.1007/s10899-023-10256-5. Acesso em: 10 nov. 2025.
MANOEL, H. Matthew Benham: Dono do Brentford fez história no mundo das apostas. Disponível em: https://www.mktesportivo.com/2025/05/matthew-benham-dono-do-brentford-fez-historia-no-mundo-das-apostas. Acesso em: 16 set. 2025.
MARCONI, Marina de Andrade; LAKATOS, Eva Maria. Técnicas de pesquisa: planejamento e execução de pesquisa, amostragens e técnicas de pesquisa, elaboração, análise e interpretação de dados. 9. ed. Rio de Janeiro: Atlas, 2021.
MATEJ, U. et al, Optimal sports betting strategies in practice: an experimental review. IMA Journal of Management Mathematics, v. 32, n. 4, p. 465–489, 2021. Disponível em: https://arxiv.org/abs/2107.08827. Acesso em: 11 dez. 2025.
MATHESON, Victor. An Overview of the Economics of Sports Gambling and an Introduction to the Symposium. Eastern Economic Journal, v. 47, n. 1, p. 1–8, 2021. DOI: 10.1057/s41302‑020‑00182‑4. Disponível em: https://pmc.ncbi.nlm.nih.gov/articles/PMC7780080/. Acesso em: 15 nov. 2025.
MATTINEN, Topias; MACEY, Joseph; HAMARI, Juho. Gambling in digital games and esports: a scoping review. Tampere: Tampere University, 2022. Disponível em: https://trepo.tuni.fi/bitstream/handle/10024/208524/0383.pdf?sequence=1. Acesso em: 22 out. 2025.
MEDRI, Dr. Waldir. Análise Exploratória de Dados. 2011. 82 f. Tese (Doutorado) - Curso de Especialização “Lato Sensu” em Estatística, Universidade Estadual de Londrina, Londrina, 2011. Disponível em: https://docs.ufpr.br/~benitoag/apostilamedri.pdf. Acesso em: 12 dez. 2025.
PELECHRINIS, Konstantinos; WINSTON, Wayne. A Skellam Regression Model for Quantifying Positional Value in Soccer. arXiv preprint arXiv:1807.07536, jul. 2018. Disponível em: https://arxiv.org/pdf/1807.07536. Acesso em: 21 out. 2025.
RAO, K.; HASTIE, R. Predicting Outcomes in a Sequence of Binary Events: Belief Updating and Gambler's Fallacy Reasoning. Cogn Sci. 2023 Jan;47(1):e13211. doi: 10.1111/cogs.13211. Acesso em: 10 dez. 2025.
RESEARCH AND MARKETS. Sports Betting Market Report 2025. Relatório de pesquisa de mercado, mar. 2025. Disponível em: https://www.researchandmarkets.com/reports/5939406/sports-betting-market-report. Acesso em: 15 nov. 2025.
SKELLAM, J. G., The Frequency Distribution of the Difference Between Two Poisson Variates Belonging to Different Populations. Journal of the Royal Statistical Society, v. 109, n. 3, p. 296, 1946. Disponível em: https://www.jstor.org/stable/2981372. Acesso em: 14 dez. 2025.
SOARES, Josiel Ferreira. Análise Preditiva: Importância e Vantagens para os Negócios. 2018. Acesso em: https://repositorio-api.animaeducacao.com.br/server/api/core/bitstreams/b78507ee-3666-4c90-ad73-c9b693d96cf7/content. Acessado em 15 dez. 2025.
TERAWONG, Chawin; CLIFF, Dave. XGBoost Learning of Dynamic Wager Placement for In-Play Betting on an Agent-Based Model of a Sports Betting Exchange. In: INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE (ICAART), 16., 2024, Rome. Proceedings... Setúbal: SCITEPRESS, 2024. p. 1-12. Disponível em: https://arxiv.org/abs/2401.06086. Acesso em: 18 nov. 2025.
THABTAH, Fadi; ZHANG, Li; ABDELHAMID, Neda. NBA Game Result Prediction Using Feature Analysis and Machine Learning. Annals of Data Science, v. 6, n. 1, p. 103–116, 2019. DOI: 10.1007/s40745‑018‑00189‑x. Disponível em: https://ideas.repec.org/a/spr/aodasc/v6y2019i1d10.1007_s40745-018-00189-x.html. Acesso em: 13 nov. 2025.
TORRANCE, J.; O’HANRAHAN, M.; CARROLL, J.; NEWALL, P. W. S. The structural characteristics of online sports betting: a scoping review of current product features and utility patents as indicators of potential future developments. Addiction Research & Theory, v. 32, n. 3, 2023. DOI: 10.1080/16066359.2023.2241350. Acesso em: 13 out. 2025.
WALSH, Conor; JOSHI, Alok. Machine learning for sports betting: should model selection be based on accuracy or calibration? arXiv preprint arXiv:2303.06021, 10 mar. 2023 (v4 fev. 2024). Disponível em: https://arxiv.org/pdf/2303.06021. Acesso em: 21 out. 2025.
WILLIAMS, R. et. al. 10. The Definition, Dimensionalization, and Assessment of Gambling Participation. 2017. Disponível em: https://opus.uleth.ca/server/api/core/bitstreams/ebb3250e-0d19-426c-b649-70e99941450b/content. Acesso em: 16 nov. 2025.
Published
How to Cite
Issue
Section
Copyright (c) 2026 Revista Processando o Saber
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos publicados pertencem à Revista Processando o Saber e seguem o padrão Creative Commons (CC BY), que permite o remixe, adaptação e criação de obras derivadas do original, mesmo para fins comerciais. As novas obras devem conter menção ao(s) autor(es) nos créditos.
