Olympic Medal Prediction Based on Machine Learning Models

Authors

  • Yiming Xiao
  • Qimao Wang

DOI:

https://doi.org/10.54097/nq5rjk33

Keywords:

Olympic Games, Medal count prediction, Great Coach Effect, medal-winning potential of emerging nations, Machine Learning Models.

Abstract

The Olympic Games are the highest stage for global sports competition, and the number of medals is an important indicator of a country's athletic strength. This study uses machine learning methods such as Gradient Boosting and Random Forest models to predict the number of gold medals and total medals for each country in the 2028 Los Angeles Olympic Games, while also exploring the medal potential of emerging nations. For countries with historical medal data, a Random Forest model is constructed with features including host country status, historical medal count, athlete ratings, and the number of events participated in. Model predictions show that traditional sports powerhouses such as the United States, China, and Russia will continue to dominate the medal table, with the host country, the United States, expected to win more medals. For emerging countries, the Gradient Boosting model predicts that eight countries have a greater than 50% chance of winning medals for the first time in 2028. Furthermore, K-means clustering analysis reveals the strengths of different countries in specific events and the impact of the host country's status on medal distribution. This study provides a comprehensive methodological framework for Olympic medal prediction and offers important references for the formulation of national sports policies.

Downloads

Download data is not yet available.

References

[1] 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, 2022, 175: 121314.

[2] Guo J, Cui D. How will the COVID-19 Pandemic Affect the Asian Games? A Joint Analysis of Olympic and Pandemic Big Data [C]//2022 7th International Conference on Signal and Image Processing (ICSIP). IEEE, 2022: 814-817.

[3] Wang Y, Wang J, Yang J, et al. STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization [J]. arXiv preprint arXiv:2501.17711, 2025.

[4] Wang Fang. Prediction of Olympic Medal Results for the 2020 Olympics Based on Neural Networks [J]. Statistics and Decision, 2019, 35 (5): 89-91.

[5] Luo Yubo, Cheng Yanfang, Li Mengyao, et al. Prediction of China's Medal Count and Overall Strength at the Beijing Winter Olympics—Based on Host Nation Effect and Grey Prediction Model [J]. Contemporary Sports Science and Technology, 2022, 12 (21): 183-185.

[6] Peng Jinqiang, Jing Longjun, Chen Shuyin, et al. Analysis of the Development Trend and Grey Forecast of Athletics Performance at the Paris Olympic Games Based on Results from the World Athletics Championships [J]. Bulletin of Sport Science & Technology Literature, 2024, 32 (4): 20–26.

[7] Hu Wenqiang. Analysis and Grey Forecasting Study of Speed Skating Performance in the 16th to 23rd Winter Olympic Games [D]. Shandong: Qufu Normal University, 2021.

[8] Yang Zhongxiu, Li Yuyu, Tu Chunjing. Study on the Development Trend of Swimming Performance in the 11th to 19th Asian Games [J]. Zhejiang Sports Science, 2024, 46 (4): 62–68.

[9] Li Haiwei. Research on the Development Trend of Athletics Events in Past Olympic Games and Grey-Markov Forecasting [D]. Jiangxi: Jiangxi Normal University, 2021.

[10] Shi Huimin, Zhang Dongying, Zhang Yonghui. Can Olympic Medals Be Predicted? — A Perspective Based on Interpretable Machine Learning [J]. Journal of Shanghai University of Sport, 2024, 48 (04): 26-36.

Downloads

Published

28-09-2025

How to Cite

Xiao, Y., & Wang, Q. (2025). Olympic Medal Prediction Based on Machine Learning Models. Highlights in Science, Engineering and Technology, 155, 219-227. https://doi.org/10.54097/nq5rjk33