Research on Momentum prediction algorithm for athletes based on the CNN-LSTM Model

Momentum has been widely recognized as a psychological factor affecting athletes' performance during sports events. Quantifying the momentum of both athletes in a match and predicting its future trends and reversals can provide effective information for coaches to make tactical decisions during a match. In this paper, taking the Wimbledon dataset as an example, the quantitative model of momentum is firstly constructed by the rank-sum-ratio evaluation method based on EWMA. Subsequently, this paper introduces the CNN network to process the data input based on the traditional LSTM network, takes the output data of the CNN network as the input layer of the LSTM network, and constructs a CNN-LSTM model to predict the change of momentum of athletes in the match, and the reversal time of momentum of athletes of both sides points. Through the model comparison analysis, this paper found that the prediction accuracy of the CNN-LSTM in different time periods is up to 85%, surpassing the LSTM network by 10%. This paper helps coaches and athletes to identify the future trend of momentum in the course of the match so that they can make reasonable tactical arrangements to achieve better performance in sports events.