Author(s)

YuXuan Liu^1,2*, MengKai Zhi^1,2

Affiliation(s)

¹School of Electrical Engineering, Qingdao University, Qingdao 266071, Shandong, China.

²School of Automation, Qingdao University, Qingdao 266071, Shandong, China.

Corresponding Author

YuXuan Liu

ABSTRACT

This paper innovatively combines the SHAP method and the random forest model to focus on the study of factors influencing the number of Olympic medals, aiming at identifying the key influencing factors and clarifying their effects. The study analyzes the importance of the factors through Random Forest, explains the specific influence mechanism of each factor with the help of SHAP values, and further quantifies and describes the influence effect by using grey prediction and double difference method. The findings of the study not only reveal the core factors affecting the number of Olympic medals and their effect paths but also provide methodological reference and empirical evidence for related studies in the field of sports, which is of practical significance for optimizing Olympic preparation strategies.

KEYWORDS

SHAP method; Random forest model; Gray prediction; Difference-in-difference

CITE THIS PAPER

YuXuan Liu, MengKai Zhi. Analysis of factors influencing the number of Olympic medals based on SHAP importance ranking and machine learning algorithm. World Journal of Information Technology. 2025, 3(4): 8-16. DOI: https://doi.org/10.61784/wjit3048.

REFERENCES

[1] Ard A B, Busse M R. Who wins the Olympic Games? Economic resources and medal totals. The Review of Economics and Statistics, 2004, 86(1): 413-417.

[2] ésénne S. Determinants of Olympic medal counts: A panel data approach. Journal of Sports Economics, 2008, 9(4): 383-395.

[3] Reinhardt C, Haans M J J, van Oort F. Spatial spillovers in Olympic medal distributions. Regional Science and Urban Economics, 2023, 96: 103895.

[4] O'Neill D P, Matthews S A, Dowling N A. Predictive Analytics in Sports: Using Machine Learning to Forecast Outcomes and Medal Tally Trends. IEEE Transactions on Big Data, 2024, 10(4): 893-905.

[5] Li X, Zhang J, Wang Y. Predicting Olympic medal counts using gradient-boosted trees. Journal of Sports Sciences, 2024, 42(5): 673-682.

[6] Ahmad S, Khan M U, Ali R. Lasso-XGBoost hybrid model for Olympic medal prediction. Knowledge-Based Systems, 2024, 281: 109243.

[7] Shi H M, Zhang D Y, Zhang Y H. Can Olympic medals be predicted? -- An Interpretable Machine Learning Perspective. Journal of Shanghai Sport University, 2024, 48(04): 26-36.

[8] Xie Q H, Qu H R, Li J F, et al. Identifying emphysema risk using nanomaterial flame retardants exposure: a machine learning predictive model based on the SHAP methodology. Frontiers in Public Health, 2025, 13: 1600729.

[9] Li R. A study on the competitive performance of women's throwing events in the 24th-32nd Olympic Games and the prediction of results in Paris. Dissertation, Qufu Normal University, 2023.