Research on Momentum Prediction of Tennis Match Based on Scoring Model and Multilayer Perceptron

Abstract

During a tennis match, players may encounter various circumstances that can significantly influence their performance. This force, known as "momentum," can drastically alter the game's flow and ultimately determine the winner. Addressing the challenge of analyzing and predicting momentum shifts, this study applied the Entropy Weight TOPSIS method combined with fuzzy comprehensive evaluation to assess player performance across technical, physical, and psychological factors. These methods provided a comprehensive analysis of the players' performance metrics, revealing patterns linked to momentum changes. Following this, Pearson correlation analysis was conducted to identify key performance indicators strongly associated with match outcomes. These indicators were then integrated into a Multilayer Perceptron (MLP) model, which demonstrated high predictive accuracy, with an R-value of 0.868, effectively capturing momentum shifts in real-time. The study's findings offer valuable insights for improving strategic decision-making during matches and hold potential applications in other fields that require real-time predictive analysis.