Predictive analytics for identifying most valuable players in the 2024 T20 cricket world cup: A comparative study of support vector regression Kernels

Abstract

Background: This study investigates the use of machine learning models, specifically support vector regression (SVR) kernels, to predict team performance and identify potential most valuable players (MVPs) in the 2024 International Cricket Council (ICC) Men's T20 World Cup. Purpose: The primary objective is to evaluate and compare the predictive accuracy of three SVR kernels—radial basis function (RBF), linear, and polynomial (poly)—to identify which model demonstrates superior predictive capabilities in the context of T20 cricket. Materials and Methods: Comprehensive data on the current 15-member squads of each participating team were collected from the official ICC website, including detailed player statistics and team performance metrics. Rigorous data preprocessing, such as deduplication and outlier detection, was performed to ensure dataset accuracy. The data were then split into training and testing sets to assess the performance of the SVR models. The three kernels—RBF, linear, and poly—were evaluated using performance metrics such as mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and R-squared (R2). Results: The RBF kernel proved to be the most accurate predictor, achieving the lowest MSE (16.43), RMSE (4.05), and MAE (2.91), along with the highest R2 (0.856). In contrast, the linear and poly kernels recorded higher error metrics and lower R2 values, indicating reduced accuracy. Predictions for potential MVPs identified Glenn Maxwell (Australia) and Andre Russell (West Indies) as standout performers, with ratings of 81.5% and 81.4%, respectively. This study highlights the superior predictive performance of the RBF kernel in the dynamic setting of T20 cricket. Conclusions: The integration of predictive analytics with pedagogical principles in coaching can optimize player development and enhance team performance. These findings offer actionable insights for team management and strategic planning in the competitive landscape of the ICC Men's T20 World Cup.