Paper Contents
Abstract
Performance analysis of players in cricket is essential for identifying strengths and weaknesses, enabling data-driven decision-making for team selection and strategy. By evaluating player performance, teams can optimize player utilization and improve overall match outcomes.This research explores the use of machine learning algorithms in predicting cricket player's performance from historical match data. We used a dataset from Kaggle which included several batting and bowling statistics to train and test the models Support Vector Machine (SVM), Random Forest, Nave Bayes, Gradient Boosting, Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN). The goal is to construct an accurate model capable of predicting and classifying players to the correct performance tier. Random Forest, Nave Bayes, and Gradient Boosting also performed well with 0.92 accuracy. The research demonstrates how machine learning can effectively support team selection, player development, and strategic planning in cricket
Copyright
Copyright © 2025 Piyush Wankar. This is an open access article distributed under the Creative Commons Attribution License.
