Author(s)

YiXu Cao

Affiliation(s)

School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, Gansu, China.

Corresponding Author

YiXu Cao

ABSTRACT

Aiming at the problem of insufficient modeling of nonlinear relationships in Olympic medal prediction, this study proposes a multivariate synergistic optimization prediction model based on XG Boost, which breaks through the limitations of existing methods that are difficult to deal with complex feature interactions and cross-trends at the same time. The study integrates the historical data of the Summer Olympics from 1984 to 2020, which covers the multidimensional features such as medal distribution, participation scale, economic indicators and hosting effect, and constructs the model by combining refined feature engineering and cross-validation to accurately quantify the marginal contribution of each factor. The results show that the average absolute error of the model is 0.89, and the root mean square error is 0.68, which predicts that the United States will lead with 150 medals, China will be second with 120 medals, and the number of medals of Russia may decline. The study demonstrates the potential of machine learning in sports forecasting to provide scientific support for sports strategy development. Dynamic variable modeling and reinforcement learning can be introduced in the future to further improve prediction accuracy and real-time performance.

KEYWORDS

Olympic medal prediction; XG Boost; Historical data; Handling complex data relationships

CITE THIS PAPER

YiXu Cao. XG Boost based medal table prediction for 2028 Olympics. World Journal of Information Technology. 2025, 3(3): 62-66. DOI: https://doi.org/10.61784/wjit3044.

REFERENCES

[1] Mo Suan, Lu Zhe. Why are great powers keen to bid for the Olympics?. International Political Science, 2024, 9(04): 38-72.

[2] Shi Huimin, Zhang Dongying, Zhang Yonghui. Can Olympic medals be predicted? --Based on Interpretable Machine Learning Perspective. Journal of Shanghai University of Physical Education, 2024, 48(04): 26-36.

[3] Luo Yubo, Cheng Yanfang, Li Mengyao, et al. Prediction of China's Medal Number and Overall Strength in Beijing Winter Olympic Games-Based on Host Effect and Gray Prediction Model. Contemporary Sports Science and Technology, 2022, 12(21): 183-186.

[4] Raja M, Sharmila P, Vijaya P, et al. Olympic Games Analysis and Visualization for Medal Prediction. 2025 International Conference on Artificial Intelligence and Data Engineering (AIDE). IEEE, 2025, 822-827.

[5] Sayeed R, Hassan M T, Rahman M N, et al. Machine Learning Models for Predicting Olympic Medal Outcomes. 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI). IEEE, 2025, 3: 1-6.

[6] Nagpal P, Gupta K, Verma Y, et al. Paris Olympic (2024) Medal Tally Prediction. International Conference on Data Management, Analytics & Innovation. Singapore: Springer Nature Singapore, 2023, 249-267.

[7] CHEN T, GUESTRIN C. XG Boost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16). 2016, 785-794.

[8] ZHANG J Y, JIN W, ZHANG H Y, et al. Research on the application of XG Boost based on quantum genetic optimization. Proceedings of the 2025 2nd International Conference on Smart Grid and Artificial Intelligence (SGAI). Piscataway: IEEE, 2025, 1461-1466.