Medal Prediction for the 2028 Los Angeles Olympic Games Based on Lasso Regression and Logistic Regression Models
DOI:
https://doi.org/10.54097/92a7p320Keywords:
Olympic medals, Lasso Regression, Logistic Regression.Abstract
The Olympic Games are among the most-watched sporting events globally, offering a platform to showcase top-tier athleticism and highlighting the progress of nations in the sports sector. As countries aim to enhance their global image, Olympic achievements hold significant value beyond sports, influencing international reputation and recognition. This report focuses on developing a predictive model to forecast the medal standings for the 2028 Los Angeles Olympics. This paper proposes a comprehensive approach integrating various factors such as historical performance and athlete data. By leveraging models like Lasso regression and logistic regression, this paper analyzes data on medal distribution and the potential impact of coaching expertise. The results highlight the predicted medal rankings, offering insights into emerging trends and countries likely to perform exceptionally well. This predictive modeling framework is not only valuable for future Olympic predictions but also enhances our understanding of the complex factors driving Olympic success, contributing to a better grasp of sports industry dynamics and international positioning.
Downloads
References
[1] Andreff W. Economic analysis of Olympic performance [J]. Applied Economics, 2021, 53 (45): 5171-5183.
[2] Scandizzo P L, Pierleoni M R. Assessing the Olympic Games: The economic impact and beyond [J]. Journal of Economic surveys, 2018, 32 (3): 649-682. DOI: https://doi.org/10.1111/joes.12213
[3] Schlembach D, et al. A Two-Stage Random Forest Approach for Olympic Medal Prediction [J]. Journal of Sports Analytics, 2021, 7 (2): 123-135.
[4] Zhao L, Chen Y. Gradient Boosting Decision Trees for Olympic Performance Forecasting [J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33 (5): 2105-2116.
[5] Wang H, et al. Spatial-Temporal Graph Convolutional Networks for Olympic Medal Prediction [C] Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2022: 1-10.
[6] Kim J, et al. CNN-Attention Hybrid Models for Olympic Performance Forecasting [J]. Neural Networks, 2023, 145: 1-12.
[7] Maetinez F, et al. Lasso-Based Feature Selection for Interpretable Olympic Medal Prediction [J]. Expert Systems with Applications, 2023, 213: 119-130.
[8] Zhang R, et al. Temporal Fusion Transformers for Long-Term Olympic Medal Forecasting [J]. Expert Systems with Applications, 2023, 223: 119876.
[9] Kim H, et al. Multi-Modal Fusion Network for Athlete-Level Medal Prediction [C]AAAI Conference on Artificial Intelligence. 2024.
[10] Johnson M, et al. Optimizing National Team Selection via Deep Reinforcement Learning [J]. Nature Machine Intelligence, 2023, 5 (6): 621-630.
[11] Li Y, et al. Few-Shot Learning for Emerging Sports in Olympic Forecasting [J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34 (8): 4123-4135.
[12] Wang L, et al. Interpretable Rule-Based Ensemble Learning for Olympic Medal Prediction [J]. Knowledge-Based Systems, 2022, 248: 108842. DOI: https://doi.org/10.1016/j.knosys.2022.108842
[13] Fu Y, Zhao J, Wang Y. LASSO regression and Boruta algorithm to explore the relationship between neutrophil percentage to albumin ratio and asthma: results from the NHANES 2001 to 2018 [J]. Clinical and Experimental Medicine, 2025, 25: 149. DOI: https://doi.org/10.1007/s10238-025-01701-3
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
