Research on the prediction of the number of 2028 Olympic Medals based on K-Means and random forest

Cheng Zhao

doi:10.54097/c895yr48

Authors

Cheng Zhao

DOI:

https://doi.org/10.54097/c895yr48

Keywords:

K-Means, ARIMA, random forest, host effect.

Abstract

In order to better predict the number of MEDALS in the next Olympic Games and provide a theoretical basis for developing resource optimization strategies, this study first classified the sports intensity of each country into four categories through K-Means clustering method, and combined the time series ARIMA model and random forest method. At the same time, the "host effect" is introduced, quantify the influence on the medal number, and introduce into the medal prediction model based on the historical award, GDP, total population, 2028, and get the medal list. Finally, the results show that the top three gold MEDALS in 2028 are: the United States, China and the United Kingdom. This study has demonstrated significant innovation in the field of sports by making a detailed division of national sports intensity, successfully constructing a targeted prediction model. This model more accurately reflects the intensity levels of sports activities and effectively utilizes the hierarchical characteristics of data, thereby making the results more precise.

Downloads

Download data is not yet available.

References

[1] SCHLEMBACH C, SCHMIDT S L, SCHREYER D, et al. Forecasting the Olympic medal distribution: A socioecono-mic machine learning model [J]. Technological Forecasting and Social Change, 2022, 175: 121314.

[2] Carron A V, Loughhead T M, Bray S R. The Home Ad-vantage in Sport Nompetitions: Courneya and Carron's (1992) Conceptual Framework a Decade Later [J]. J SportsSci, 2005, 23 (4): 395 - 407.

[3] Wilson D, Ramchandani G. An Investigation of Home Advantage in the Summer Paralympic Games [J]. Sport Sciences for Health, 2017, 13 (3): 625 - 633.

[4] Mimenbayeva A, Artykbayev S, Suleymanov R, et al. Determination of the number of clusters of normalized vegetation indices using the k-means algorithm [J]. Eastern-European Journal of Enterprise Technologies, 2023, 5 (2): 42 - 55.

[5] Feng J, Huang B. Forecasting Carbon Emission Using ETS Exponential Smoothing, ARIMA and Regression with ARIMA errors Techniques [J]. International Journal of Engineering and Technology, 2024, 16 (3).

[6] Johansson U, Boström H, Löfström T, et al. Regression conformal prediction with random forests. [J]. Machine Learning, 2014, 97 (1-2): 155 - 176.

[7] Indrayudh G, Giles H. Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and Its Variance Estimate [J]. Journal of Computational and Graphical Statistics, 2020, 30 (2): 493 - 502.

[8] Mantas J C, Castellano G J, Moral-García S, et al. A comparison of random forest-based algorithms: random credal random forest versus oblique random forest [J]. Soft Computing, 2019, 23 (21):10739 - 10754.

[9] Xue L, Jiameng Z, Yong Z, et al. Clustering and Bellerophon state in Kuramoto model with second-order coupling. [J]. Chaos (Woodbury, N. Y.), 2019, 29 (4): 043102.

[10] Basariya N M, Murugesan P. An approach to arrive at stationarity in time series data [J]. International Journal of Applied Management Science, 2022, 14 (3): 221 - 245.

[11] Belashov Y V, Belashova S E, Asadullin I A. Testing the time series for stationarity in systems for processing of experimental data [J]. Radio physics and quantum electronics, 2013, 55 (9): 587 - 592.

[12] Davies N, Petruccelli D J. On the Use of the General Partial Autocorrelation Function for Order Determination in ARMA (p, q) Processes [J]. Journal of the American Statistical Association, 2012, 79 (386): 374 - 377.

[13] A New Algorithm for Automated Box-Jenkins ARMA Time Series Modeling Using Residual Autocorrelation/Partial Autocorrelation Functions [J]. Industrial Engineering & Management Systems, 2006, 5 (2): 116 - 125.

[14] BERNARD A B, BUSSE M R. Who wins the Olympic Games: Economic resources and medal totals [J]. Reviewof Economics and Statistics, 2004, 86 (1): 413 - 417.

[15] Genetic Algorithms; Findings on Genetic Algorithms Detailed by Investigators at Otsuma Women's University (Optimization technique by genetic algorithms for international logistics) [J]. Journal of Technology & Science, 2014.