Author(s)

YiFan Guo

Affiliation(s)

College of Physics, East China University of Science and Technology, Shanghai 200237, China.

Corresponding Author

YiFan Guo

ABSTRACT

With the successful conclusion of the 2024 Summer Olympics in Paris, the Olympic medal table rankings have been finalized. The medal table is not only the personal honor of athletes, but also a symbol of the comprehensive strength and national cohesion of countries. Therefore, the research on the prediction of Olympic medal list has received wide attention. However, the current Olympic performance prediction research mainly focuses on macro factors and ignores micro variables, while multiple linear regression can deal with the relationship between multiple independent variables and one dependent variable, which becomes an ideal solution to this complex prediction problem. First and foremost, this paper develops multivariate linear regression models to predict the number of gold medals and the total number of medals for athletes, respectively. These models are used to predict their performance in the 2028 Los Angeles Olympic Games. After obtaining the predicted value of medals won by athletes in 2028, the predicted medal counts of athletes from each country are summed up to initially obtain the medal predictions of each country. In addition, considering that the actual number of national medals will be affected by the host country and the type of program, so this paper establishes a multiple linear regression model to predict the interference of the host country and the type of program on the actual number of medals of each country, and thus, constructs a more accurate medal prediction model. The final prediction result is: the total number of medals and the total number of gold medals is ranked first by the United States as the host country, followed by the United Kingdom, Germany, China and so on, of which France and Australia have the same number of medals and are tied for the fifth place. According to the above rankings, the United Kingdom, France and Germany have improved compared with the previous Olympic Games, while China, Australia and Japan have declined compared with the previous Olympic Games.

KEYWORDS

Multiple linear regression; Host effect; Olympic medal prediction; F-tests

CITE THIS PAPER

YiFan Guo. Forecasting Olympic medal counts: a multiple linear regression model. World Journal of Information Technology. 2025, 3(3): 47-53. DOI: https://doi.org/10.61784/wjit3042.

REFERENCES

[1] Zhao Xin, Xue Ye, Niu Chonghuai. Correlation Analysis of the Total Number of Olympic MEDALS of Various Countries and the Total GDP. Sports Culture Guide, 2013, (08): 1-4.

[2] Zhang Yuhua. Medal Count Prediction of China's 31st Olympic Games Based on Linear Regression Dynamic Model. Journal of henan normal university (natural science edition), 2013, 9(02): 24-26+60. 

[3] 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.

[4] Vagenas G, Vlachokyriakou E. Olympic medals and demo-economic factors: Novel predictors, the ex-host effect, the exact role of team size, and the “population-GDP” model revisited. Sport Management Review, 2012, 15(2): 211-217.

[5] 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.

[6] Griffiths W E, Hill R C. On the Power of the F-test for Hypotheses in a Linear Model. The American Statistician, 2022, 76(1): 78-84.

[7] TIAN Hui, HE Yiman, WANG Min, et al. Medal Prediction and Participation Strategy of Chinese Athletes in the 2022 Beijing Winter Olympics-Based on the Analysis of Olympic Home Field Advantage Effect. Sports Science, 2021, 41(02): 3-13+22. 

[8] Luo Yubo, Cheng Yanfang, Li Mengyao, et al. Forecasting the number of medals and overall strength ofChina in the Beijing Winter Olympics - Based on host effect and gray prediction model. Contemporary Sports Science and Technology, 2022, 12(21): 183-186.