Analysing the impact of field conditions, pitch features, and opponent strength on cricket performance: A machine learning approach

Abstract

Cricket, a sport that is beloved worldwide, requires a combination of expertise, and strategic intelligence. This exposition explores the study of cricket performance, specifically examining how factors such as playing circumstances, pitch dynamics, and the qualities of opponents affect the effectiveness of bowlers and the skill of hitters. The study tries to discover underlying patterns and relationships between these characteristics and player success by using rigorous statistical analysis and other machine learning techniques. Assessment criteria, including accuracy, mean absolute error (MAE), root mean square error (RMSE), and R2 scores, are used to measure the prediction effectiveness of the models. The findings highlight the significant influence of the quality of opponents, the features of the pitches, and the circumstances of the field on the performance of players. In addition, the analysis clarifies the predictive ability of several machine learning algorithms, highlighting Random Forest, XGBoost, and LightGBM as the most precise models. These discoveries provide useful knowledge for academics, educators, and cricket enthusiasts, enabling a better understanding of the various factors that influence player performance and promoting informed strategy discussions.

Keywords

• cricket analytics
• machine learning
• player performance analysis
• prediction analysis
• statistical modelling