Predicting Esports Player Ratings Through Tournament Statistics and Comparative Regression-Based Machine Learning Model Evaluation
bit-Tech · 10.08.2026 · 9 (1) · 955-965
DOI: 10.32877/bt.v9i1.4020 ↗Kurz gefasst
Fachartikel in der Zeitschrift bit-Tech, online erschienen am 10.08.2026. Verfasst von Muhammad Satrio Prayoga und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The growing professionalization of esports has increased the need for objective, data-driven approaches to evaluate player performance and support talent identification. This study compares Multiple Linear Regression and Support Vector Regression (SVR) in predicting esports player ratings using tournament-based performance statistics. This study is limited to Counter-Strike tournament statistics obtained from a Kaggle dataset, with three statistical predictors: rounds played, kill–death difference, and kill–death ratio. The dataset was processed through data cleaning, feature selection, normalization for SVR, and a hold-out validation scheme with an 80:20 training–testing split. Model performance was evaluated using Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and Mean Absolute Percentage Error. The results show that both models produced low prediction errors, indicating that the selected performance statistics have strong predictive relevance for player rating estimation. However, SVR consistently achieved lower error values than Multiple Linear Regression, with an RMSE of 0.0476, MAE of 0.0377, and MAPE of 4.03%, compared with RMSE of 0.0529, MAE of 0.0402, and MAPE of 4.30% for Multiple Linear Regression. These findings suggest that kernel-based regression provides a modest but consistent improvement in modeling rating patterns within esports performance data. The study contributes to predictive analytics in esports by offering an empirical comparison of regression-based models for supporting more transparent player evaluation, scouting, and recruitment decisions.
Zitieren
APA
Prayoga, M. S., & Sugianti, D. (2026). Predicting Esports Player Ratings Through Tournament Statistics and Comparative Regression-Based Machine Learning Model Evaluation. bit-Tech, 9(1), 955-965. https://doi.org/10.32877/bt.v9i1.4020
Vancouver
Prayoga MS, Sugianti D. Predicting Esports Player Ratings Through Tournament Statistics and Comparative Regression-Based Machine Learning Model Evaluation. bit-Tech. 2026;9(1):955-965. doi:10.32877/bt.v9i1.4020
BibTeX
@article{Prayoga2026,
author = {Prayoga, Muhammad Satrio and Sugianti, Devi},
title = {Predicting Esports Player Ratings Through Tournament Statistics and Comparative Regression-Based Machine Learning Model Evaluation},
journal = {bit-Tech},
year = {2026},
volume = {9},
number = {1},
pages = {955--965},
doi = {10.32877/bt.v9i1.4020}
}
EUVIMED