Race Momentum Study Based on LSTM Algorithm and EWM-TOPSIS Model

In this study, the entropy weight method (EWM) and TOPSIS method are integrated, and finally an EWM-TOPSIS athlete performance evaluation (ETP) model is formed, which uses the average of two weights to effectively reduce the errors caused by the limitations of the model itself. This innovative evaluation framework can describe and quantify the "momentum score" for players according to carefully selected performance indicators. Pearson correlation coefficient is used to evaluate the correlation between momentum score and real-time winning probability, and to evaluate the performance of different function combinations in the momentum transfer prediction (MSP) model based on LSTM, and to determine the key factors affecting the final result. In a word, our research not only confirms the indispensable role of momentum in all kinds of sports, but also reveals a complex framework for predicting and analyzing game dynamics, providing valuable insights for athletes, coaches and sports analysts.