In cricket, automation for learning, analyzing, guessing, and predicting is important. As cricket is a sport that is having high demand, no one knows who will win the game until the last over. And there are various factors inclusive of men or women, crew performances, and some diverse environmental elements that need to be taken into consideration in planning a recreation method as a result, we decided to create a machine-learning model to analyze the game using previous match data For this interest, we used a records evaluation and statistical equipment to procedure statistics and bring some suggestions. Implemented models can help selection makers throughout cricket games to test a crew’s strengths in competition to the other and environmental elements. Right here we’re got used sklearn, preprocessing, and label encoder, and for compilation were got used random woodland classifier set of rules to illustrate the conditions and recommendations for problem fixing We can also predict match outcomes from past experiences by using some algorithms like Support Vector Machine (SVM), Naive Bayes, k-Nearest Neighbor (KNN) are used for classification of match winner and Linear Regression and decision tree for the prediction of an inning’s score. The dataset contains huge data on the previous performance of bowlers and batsmen in matches, many Seven features have been identified that can be used for prediction. Based on those features, models are built and evaluated using certain parameters.

Keywords : Random Forest Classifier, Support Vector Machine (SVM), Naive Bayes, k-Nearest Neighbor (KNN), NumPy, Data Mining, Analysis.