Author(s)

QiuLin Yao^1*, Feng Cheng¹, YanPeng Guo¹, KuiSong Wang¹, QiSheng Liu¹, Ning Ding²

Affiliation(s)

¹School of Mechanical Engineering, Jiamusi University, Jiamusi 154007, Heilongjiang, China.

²School of Materials Science and Engineering, Jiamusi University, Jiamusi 154007, Heilongjiang, China.

Corresponding Author

QiuLin Yao

ABSTRACT

This paper proposes a robust and data-driven methodology to forecast Olympic medal outcomes with high accuracy and interpretability. A sequence-to-sequence (Seq2Seq) neural architecture is employed to learn temporal dependencies in national Olympic performance, while hyperparameter optimization is conducted using a Tree-structured Parzen Estimator (TPE) to enhance model generalization. To ensure data integrity, preprocessing steps include structured data cleansing and the use of a backpropagation neural network to address missing values. The model further integrates features such as national investment in sports, historical medal trends, and host country effects. In addition to deterministic predictions, uncertainty is quantified through Monte Carlo sampling and confidence intervals, providing probabilistic insights into future outcomes. Experimental results show that the proposed approach outperforms baseline models, achieving an R² improvement from 0.827 to 0.875 on the test dataset. The framework is applied to predict the medal distribution for the 2028 Los Angeles Olympics and highlights emerging medal-winning countries. These findings demonstrate the framework’s potential to assist national committees and policy makers in strategic planning for future Olympic participation.

KEYWORDS

Olympic medal forecasting; Sequence-to-sequence neural network; Bayesian hyperparameter optimization; Prediction uncertainty quantification

CITE THIS PAPER

QiuLin Yao, Feng Cheng, YanPeng Guo, KuiSong Wang, QiSheng Liu, Ning Ding. A Hybrid Seq2Seq and Bayesian optimization framework for predicting Olympic medal distribution with uncertainty analysis. World Journal of Information Technology. 2025, 3(2): 54-60. DOI: https://doi.org/10.61784/wjit3034.

REFERENCES

[1] Shi Huimin, Zhang Dongying, Zhang Yonghui. Can Olympic medals be predicted? Journal of Shanghai Sport University, 2024, 48(04): 26-36.

[2] Chen Zhanshou, Liang Yan, Wei Qiuyue. Examination of structural variation points in linear regression models with LMSV errors. System Science and Mathematics, 2025: 1-18.

[3] Xiong Zhongmin, Guo Huaiyu, Wu Yuexin. A review of research on missing data processing methods. Computer Engineering and Applications, 2021, 57(14): 27-38.

[4] Denicolò V, Polo M. Duplicative research, mergers and innovation. Economics Letters, 2018, 166: 56-59.

[5] L Zhang, B Ding, JY Deng, et al. Study on urban subsurface change and runoff coefficient response based on BP neural network. Journal of Changjiang Academy of Sciences, 2025: 1-7.

[6] LUO Min, YANG Jinfeng, YU Hui,et al. A short-term load forecasting method based on TPE optimization and integrated learning. Journal of Shanghai Jiao Tong University, 2023(5).

[7] Li W J, Wu LL, Wen SH, et al. Optimization of LSTM-Seq2seq model for runoff simulation based on attention mechanism. Glacial Permafrost, 2024, 46(3): 980-992.

[8] You Lan, Han Xuewei, He Zhengwei, et al. An Improved Seq2Seq-Based Model for Short-Term AIS Trajectory Sequence Prediction. Computer Science, 2020, 47(09): 169-174.