Predictive Modeling of T20 Opener Success in International Cricket Tournaments via Machine Learning Models

In the game of cricket, particularly during high-stakes tournaments, players’ performances have substantial consequences for their teams and energetic crowd. Predicting players’ outcomes is often validated by experts’ territory through mathematical and statistical models. However, due to the intricacies of cricket, player-related features in different sports cannot be evaluated comparatively. De spite these challenges, the rising utilization of Machine Learning (ML) models has proven crucial role in achieving precise predictions. In this research study, the ultimate aim was to predict the performance of T20 opening batters for upcoming T20 tournaments. Player records were compiled from ESPNcricinfo and Cricbuzz. Several ML models are implemented to predict players’ outcomes. The analysis for this study was categorized into two cases: runs scored and strike rate, acknowledging both pre-match and all-match features. For predicting outcomes based on runs scored using pre-match features, Decision Tree and Naïve Bayes outperformed with an accuracy of 0.75, while for strike rate, K-Nearest Neighbor surpassed models with an accuracy of 0.68. Furthermore, assessing players’ performance on