Franchise owners are becoming more prepared to spend money on top players between the ages of 20 and 30 in local twenty20 cricket tournaments like the Indian Premier League and others. Player recruitment is the most crucial and time-consuming task in cricket since it affects the team’s chances of success. A team runs the danger of losing the championship and possibly millions of dollars if they spend for the wrong player. This has led to a great deal of effort being invested into creating machine learning models that can predict a cricket player’s performance. The goal of this research is to ascertain whether machine learning can be used to identify prospective young and middle-aged players, who are between the ages of 20 and 30, based only on their historical statistics. Two different methods of machine learning have been applied in this work. The effectiveness of Random Forest and Naive Bayes machine learning algorithms has been evaluated through study utilizing a range of criteria, including accuracy, precision, and so on. Predictions regarding the total amount of runs scored by batsmen and wickets taken by bowlers have been made using both of these models. The highest accurate classifier for predicting wickets taken and runs scored was found to be the Random Forest Classifier.