Capturing Momentum: Tennis Match Analysis Using Machine Learning and Time Series Theory

TL;DR

This paper employs machine learning and time series models to analyze tennis match momentum, aiming to predict match outcomes and assess player performance through statistical and feature importance analyses.

Contribution

It introduces a combined approach using Hidden Markov Models, XGBoost, and LightGBM to model and evaluate tennis match momentum and player performance.

Findings

Hidden Markov Models effectively predict momentum shifts.

XGBoost confirms the significance of momentum features.

LightGBM achieves high performance in model evaluation.

Abstract

This paper represents an analysis on the momentum of tennis match. And due to Generalization performance of it, it can be helpful in constructing a system to predict the result of sports game and analyze the performance of player based on the Technical statistics. We First use hidden markov models to predict the momentum which is defined as the performance of players. Then we use Xgboost to prove the significance of momentum. Finally we use LightGBM to evaluate the performance of our model and use SHAP feature importance ranking and weight analysis to find the key points that affect the performance of players.