Modeling and Analysis of Olympic Medal Table Based on Multiple Features

HanBang Chen, Delin Kong, Biao Jin, CaiLing Huang, YiXiang Ke, MingCheng Zhang, GuanHua Li, Chao Tan
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:726-733, 2025.

Abstract

In the first part, this study first used the winning records and medal data of Olympic competitions. Based on the relevant variation characteristics of medal counts, their impact was assessed by quantifying the fluctuation of medal counts under multiple characteristics. For medal counts, they were incorporated into a medal prediction model under time series through stacked integration. LR, LASSO, SVM, and Catboost were used as base leaners in the first layer ; RF, XGBoost, and LightGBM were used in the second layer of the meta-learner; and the optimal stacked integration learning for medal count prediction under time series was subsequently determined. Subsequently, the medal standings for the 2028 Summer Olympics in Los Angeles, USA were predicted under dynamic simulation as the entire sequential system was varied. Based on the parameter-adjusted feature structure of countries without medal counts, two evaluation models were constructed, one of which was initialized with a fixed medal-associated parameter ratio. According to the model framework, the impact of no medal data is parameterized according to the model parameter distribution law to complete the analysis of countries with no medal counts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-chen25d, title = {Modeling and Analysis of Olympic Medal Table Based on Multiple Features}, author = {Chen, HanBang and Kong, Delin and Jin, Biao and Huang, CaiLing and Ke, YiXiang and Zhang, MingCheng and Li, GuanHua and Tan, Chao}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {726--733}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/chen25d/chen25d.pdf}, url = {https://proceedings.mlr.press/v278/chen25d.html}, abstract = {In the first part, this study first used the winning records and medal data of Olympic competitions. Based on the relevant variation characteristics of medal counts, their impact was assessed by quantifying the fluctuation of medal counts under multiple characteristics. For medal counts, they were incorporated into a medal prediction model under time series through stacked integration. LR, LASSO, SVM, and Catboost were used as base leaners in the first layer ; RF, XGBoost, and LightGBM were used in the second layer of the meta-learner; and the optimal stacked integration learning for medal count prediction under time series was subsequently determined. Subsequently, the medal standings for the 2028 Summer Olympics in Los Angeles, USA were predicted under dynamic simulation as the entire sequential system was varied. Based on the parameter-adjusted feature structure of countries without medal counts, two evaluation models were constructed, one of which was initialized with a fixed medal-associated parameter ratio. According to the model framework, the impact of no medal data is parameterized according to the model parameter distribution law to complete the analysis of countries with no medal counts.} }
Endnote
%0 Conference Paper %T Modeling and Analysis of Olympic Medal Table Based on Multiple Features %A HanBang Chen %A Delin Kong %A Biao Jin %A CaiLing Huang %A YiXiang Ke %A MingCheng Zhang %A GuanHua Li %A Chao Tan %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-chen25d %I PMLR %P 726--733 %U https://proceedings.mlr.press/v278/chen25d.html %V 278 %X In the first part, this study first used the winning records and medal data of Olympic competitions. Based on the relevant variation characteristics of medal counts, their impact was assessed by quantifying the fluctuation of medal counts under multiple characteristics. For medal counts, they were incorporated into a medal prediction model under time series through stacked integration. LR, LASSO, SVM, and Catboost were used as base leaners in the first layer ; RF, XGBoost, and LightGBM were used in the second layer of the meta-learner; and the optimal stacked integration learning for medal count prediction under time series was subsequently determined. Subsequently, the medal standings for the 2028 Summer Olympics in Los Angeles, USA were predicted under dynamic simulation as the entire sequential system was varied. Based on the parameter-adjusted feature structure of countries without medal counts, two evaluation models were constructed, one of which was initialized with a fixed medal-associated parameter ratio. According to the model framework, the impact of no medal data is parameterized according to the model parameter distribution law to complete the analysis of countries with no medal counts.
APA
Chen, H., Kong, D., Jin, B., Huang, C., Ke, Y., Zhang, M., Li, G. & Tan, C.. (2025). Modeling and Analysis of Olympic Medal Table Based on Multiple Features. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:726-733 Available from https://proceedings.mlr.press/v278/chen25d.html.

Related Material