Machine learning XGBoost and SHAP models for Chinese Women's Basketball League game outcome prediction and quantitative analysis methodology

This study investigated the application of artificial intelligence in real-time prediction of Chinese Women's basketball games, identifying the technical-tactical indicators within performance that are critical in determining the outcomes of the games. Utilizing games data from the Chinese Women's basketball seasons 2021 to 2024 as the sample, this study constructed a real-time predictive model for Chinese Women's basketball game outcomes, integrating the machine learning XGBoost and SHAP algorithms. The model simulated the prediction of game outcomes at different time of games and effectively quantified the analysis of key technical-tactical indicators that influenced game outcomes. The results of this study indicate that the XGBoost algorithm is highly effective in predicting the outcomes of games in the Chinese Women's Professional Basketball League. Key performance indicators such as assists, defensive rebounds, points from turnover, successful two-point field goals are consistently correlated with game outcomes. When teams play at home, second chance points are a crucial factor influencing the game result. On the other hand, when teams play away games, turnovers become the key factors. The real-time prediction model for game outcomes in the Chinese Women's Professional Basketball League integrates the XGBoost algorithm and SHAP, offering excellent performance and high interpretability. By quantifying the factors that determine victory, it provides critical decision support for coaches in devising tactical strategies on the court.