Cricket performance predictions: a comparative analysis of machine learning models for predicting cricket player’s performance in the One Day International (ODI) world cup 2023

Abstract

Background and purpose
 Cricket, a globally renowned bat and ball sport, is the second most popular sport worldwide. The objective of the study is to utilize machine learning algorithms to predict the performance probabilities of Indian cricket players participating in the ODI Cricket World Cup 2023. Furthermore, we aim to assess and compare the predictive precision of three machine learning models such as, Random Forest, Support Vector Regression, and XGBoost.
 Materials and Methods
 Data collection centered on Indian One Day International cricket statistics, encompassing matches played, batting and bowling averages, catches taken, and performance predictions. We sourced this data from reputable platforms such as ESPNcricinfo and the International Cricket Council website. Our performance prediction utilized of three machine learning models such as, Random Forest, Support Vector Regression, and XGBoost. Comparative analysis was conducted, evaluating these models through essential metrics including Mean Squared Error, Root Mean Squared Error, Mean absolute Error, and R-squared.
 Results
 The comparative analysis revealed that the XGBoost model consistently outperformed the others. It exhibited lower errors with the lowest Mean Squared Error, Root Mean Squared Error, and Mean Absolute Error, signifying greater predictive accuracy. XGBoost achieved the highest R-squared value, indicating a robust relationship between predictions and actual performance probabilities. Random Forest produced satisfactory results but fell short of XGBoost's accuracy, while Support Vector Regression displayed less accurate predictions across all metrics.
 Conclusions
 This research demonstrates the superior predictive ability of the XGBoost model in the performance probabilities of Indian cricket players in the ODI Cricket World Cup. The practical implications underscore the significance of data-driven insights for team selection and strategy.