Predicting game outcomes has significantly garnered the interest of researchersin recent years. The role of player performance is integral in-game analytics, significantlyimpacting the interpretation and results of the analysis. Quantifyingfactors impacting tennis games would advance the analysis of player’s performance.The proposed work intends to use real-time data from each game pointto determine essential feature values, formulate and assess the impact of psychologicalmomentum, and employ machine learning methodology on mid-matchdata for predicting the game’s victor. The data source is from Wimbledon and US Open games from 2017 to 2022, a total of 1592 games, and utilize 363 gamesof 2023 to evaluate their forecasting ability. We first obtained weights throughinformation entropy and defined psychological momentum, and then 3 best classifiers,random forest, CatBoost, and Logistic Regression, were detected to assessthe features. Additionally, we implemented a soft voting ensemble method integratingthe Random Forest and CatBoost classifiers. All four models achieve over90% accuracy and F1-score, with the soft voting classifier performing the best(accuracy: 97.5%, F1 score: 97.4%). These models achieve predictive accuraciesabove 70% using the first 25% data of a game.