A Study on Olympic Medal Prediction Based on Random Forest and Polynomial Regression
DOI:
https://doi.org/10.54097/0y8dzd10Keywords:
Medal Prediction, Clustering Model, Random Forest, Polynomial Regression.Abstract
The Olympic medal table serves as a symbol of a nation's sporting competitiveness, and fluctuations in medal counts reflect underlying patterns within complex data. This study aims to uncover the mathematical logic behind the competition for medals and to identify the intrinsic relationships between these patterns and historical data. Based on attributes that reflect a country's medal-winning potential, a predictive model is constructed to estimate medal counts with a high degree of accuracy. Specifically, six key factors influencing medal counts are identified and integrated into a random forest regression model. A clustering model based on comprehensive indicators is applied to classify and quantify countries according to their Olympic performance. Polynomial regression is then employed to forecast relevant data for the 2028 Olympic Games. These forecasts are subsequently used to predict the number of medals in 2028 using the trained random forest model, and prediction intervals are established based on the MAPE error range.The model’s performance is evaluated using MSE, MAE, and R2 metrics for gold, silver, bronze, and total medal predictions. Results show low prediction errors and strong goodness-of-fit, with R² values of 0.93588, 0.96743, 0.96554, and 0.83254, respectively. These outcomes indicate that the model demonstrates high predictive accuracy and robustness across all medal categories.
Downloads
References
[1] Forrest D, Sanz I, Tena J D. Forecasting national team medal totals at the Summer Olympic Games[J]. International Journal of Forecasting, 2010, 26(3): 576-588. DOI: https://doi.org/10.1016/j.ijforecast.2009.12.007
[2] Peters T. Winning against the odds: A socio-economic analysis of Olympic success[D]. Erasmus University, 2023.
[3] Schlembach C, Schmidt S L, Schreyer D, et al. Forecasting the Olympic medal distribution during a pandemic: a socio-economic machine learning model[J]. arXiv preprint arXiv:2012.04378, 2020. DOI: https://doi.org/10.2139/ssrn.3745595
[4] Bunn J, Reagor M K, Myers B J. Creating a random forest model to determine success in women’s collegiate lacrosse[J]. Journal of Sport and Human Performance, 2025, 13(1): 1-9.
[5] Zhao K, Du C, Tan G. Enhancing basketball game outcome prediction through fused graph convolutional networks and random forest algorithm[J]. Entropy, 2023, 25(5): 765. DOI: https://doi.org/10.3390/e25050765
[6] Alnahit A O, Mishra A K, Khan A A. Stream water quality prediction using boosted regression tree and random forest models[J]. Stochastic Environmental Research and Risk Assessment, 2022, 36(9): 2661-2680. DOI: https://doi.org/10.1007/s00477-021-02152-4
[7] Guo Z, Yu B, Hao M, et al. A novel hybrid method for flight departure delay prediction using Random Forest Regression and Maximal Information Coefficient[J]. Aerospace Science and Technology, 2021, 116: 106822. DOI: https://doi.org/10.1016/j.ast.2021.106822
[8] Liu J, Liang D, Cho H. A polynomial regression model for predicting knuckleball movements in soccer free-kick[J]. Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology, 2025: 17543371241311676. DOI: https://doi.org/10.1177/17543371241311676
[9] Belany P, Hrabovsky P, Sedivy S, et al. A comparative analysis of polynomial regression and artificial neural networks for prediction of lighting consumption[J]. Buildings, 2024, 14(6): 1712. DOI: https://doi.org/10.3390/buildings14061712
[10] Tabelini L, Berriel R, Paixao T M, et al. Polylanenet: Lane estimation via deep polynomial regression[C]//2020 25th international conference on pattern recognition (ICPR). IEEE, 2021: 6150-6156. DOI: https://doi.org/10.1109/ICPR48806.2021.9412265
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
