As one of the largest sporting events in the world

the medal performance of each country in the Olympic Games not only reflects the competitive level

but also reflects the comprehensive strength of the country's sports development. With the increasingly fierce competition in the Olympic Games

accurate medal prediction provides an important reference for the strategic planning

resource allocation and preparation of each country. This paper proposes a medal prediction method based on the Lasso regression model. By analyzing the US Olympic medal data from 1986 to 2024

a regression model for predicting the medal table of the 2028 Los Angeles Summer Olympics was established. In order to improve the accuracy of the model

feature standardization

cross-validation and uncertainty estimation were performed. The results show that the United States and China are still in the leading position in the number of gold medals and total medals

with the predicted number of gold medals being 42 and 40 respectively

and the estimated number of total medals being 129 and 88 respectively. This paper also evaluates the uncertainty of the prediction results through confidence interval analysis

providing strong support for policymakers on the trend of future Olympic competitions. Finally

this paper discusses future research directions

including how to deal with emerging variables and further improve the accuracy and stability of the model.