Predicting The Medal Distribution of Countries in the 2028 Los Angeles Olympics Based On OP-Xgboost
DOI:
https://doi.org/10.54097/e4bhgf55Keywords:
Optuna, XGBoost, Medal Prediction Model.Abstract
This study aims to predict the medal distribution of various countries at the 2028 Los Angeles Olympics. Through data cleaning and feature engineering, a dataset was constructed that includes key indicators such as population size, GDP, per capita income, and sports development index.Innovatively proposed and applied the XGBoost model combined with the Optuna hyperparameter optimization framework (OP-XGBoost), significantly improving the model's prediction accuracy (medal count prediction R² increased from 0.636 to 0.716, and gold medal count R² increased from 0.563 to 0.635). The model prediction results show that the United States will maintain its dominance in sports, it is expected to win a total of 138 medals (46 gold medals), with a prediction range of [88, 140]; China closely follows, expected to win 97 medals (42 gold medals), with a prediction range of [24, 52]. Countries like the UK and Japan are expected to be in the second tier. An analysis of national performance trends indicates the United States has made the most significant progress (+92.5%), mainly due to the continuous increase in sports investment; on the other hand, the Unified Team's performance is expected to decline significantly (-77.9%), possibly due to the instability in the development of its athlete pipeline. This study provides a quantitative analysis to understand the relationship between a country's overall strength and its Olympic performance, verifies the effectiveness of machine learning in sports prediction, and offers data support and model references for countries to develop differentiated Olympic preparation strategies.
Downloads
References
[1] Zhang Yuhua. Model Construction and Quantitative Analysis of Olympic Medal Count and Five Influencing Factors [J]. Shandong Sports Science and Technology,2013, 35 (3): 43-47.
[2] Shi Huimin. Can Olympic Medals Be Predicted from the Perspective of Explainable Machine Learning. 2024-08-06.
[3] Wang Fang. Prediction of Medal Results for the 2020 Olympic Games Based on Neural Network [J]. Statistics and Decision,2019, 35 (5): 89-91.
[4] Feng Jing. Research on Spatial Prediction of Precipitation in Shaanxi Province Based on XGBoost Algorithm [D]. Xi'an: Xi'an University of Technology,2023.
[5] Liu Zhibin, Hao Jianlong, Sun Qiwei. Research on Stock Trend Prediction Method Based on Improved Transformer and Hypergraph Model [J]. Journal of Intelligent Systems, 2024, 19 (5): 1092-1101.
[6] Wang Shiyu. Prediction Model of Olympic Medals Based on Nonlinear Regression and BP Neural Network [J]. Sports Goods and Technology, 2017(24): ZL.
[7] Liao Bin, Wang Zhi Ning. A Method for Predicting the Value of Football Players and Analyzing Their Features by Integrating XGBoost and SHAP Models [J]. Computer Science,2022, 49 (12): 195-204.
[8] Souza G. Machine-Learning-Olympic-Medal-Prediction [EB/OL]. (2024-04-01) [2025-07-28].
[9] inheiro J M H, Becker M. Breast Cancer Classification Using Gradient Boosting Algorithms Focusing on Reducing the False Negative and SHAP for Explainability[J]. arXiv preprint arXiv:2403.09548, 2024.
[10] Schlembach C, Schmidt S L, Schreyer D, et al. Forecasting the Olympic medal distribution – A socioeconomic machine learning model[J]. Technological Forecasting and Social Change, 2021, 175: 121314 DOI: https://doi.org/10.1016/j.techfore.2021.121314
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.
