Research on Olympic medal prediction based on GA-BP and logistic regression model Extended data

Background:Predicting the number and distribution of Olympic medals in the future has become a hottopic, but predictingthe number of Olympic medalsis not easyand requires comprehensive consideration of multiple factors such as historical data, athleteperformance,and host country effects.Method:This article uses the GA-BP algorithm model, combined withgenetic algorithm (GA) and backpropagationneural network (BPNN),to optimize the weightsand bias parameters of the BP neural networkusing the global search capability of genetic algorithm, thereby improvingtraining efficiency and prediction performance.By estimating the number of Olympic gold medals and total medals, verifying the accuracy of the model, and predicting the medal table forthe 2028 Los Angeles Olympics. Meanwhile, basedon the synthetic control model, Estonia and China were selected as research subjects to constructa virtual control group and two experimental groupsfor analysis.

研究背景：未来奥运会奖牌数量与分布的预测已成为热门研究议题，但奥运会奖牌数量预测难度较大，需综合考量历史数据、运动员表现、主办国效应等多方面因素。研究方法：本文采用GA-BP算法模型，结合遗传算法（Genetic Algorithm, GA）与反向传播神经网络（Backpropagation Neural Network, BPNN），利用遗传算法的全局搜索能力优化BP神经网络的权重与偏置参数，以此提升训练效率与预测性能。通过对奥运会金牌总数与奖牌总数量进行估算，验证模型的准确性，并对2028年洛杉矶奥运会奖牌榜进行预测。同时，本文基于合成控制模型，选取爱沙尼亚与中国作为研究对象，构建虚拟对照组与两个实验组开展分析。