Player Performance Prediction in Sports Using Machine Learning

This research uses cutting-edge machine learning techniques to develop predictive models for player performance in the sports of hockey, kabaddi, and cricket. By utilising historical data including runs scored, number of outs, number of wins, and fitness records, the goal is to revolutionise the traditional methods of player evaluation. Our predictive models’ fundamental building blocks are machine learning algorithms, such as naïve bayes , and linear regression. The results should provide sports decision-makers with precise information about a player's abilities and suitability for upcoming games. Additionally, an interactive dashboard built with software like Tableau and Power BI will make predictions easy to visualise and share. It aims to improve team performance and decision- making by bridging the gap between data analytics and sports management.