Enhancing ODI Cricket Score Forecasting Using AI: A Data-Driven Approach with Machine Learning Models

Cricket’s popular international (ODI) version is famous for achieving a balance between the quick thrill of Twenty20 matches and the depth of strategy of Test matches. It’s very hard to forecast the score in this game. To enhance the accuracy of prediction, we will focus on using advanced machine learning techniques to predict cricket scores in (ODI) matches. Employing techniques such as Multi-Linear Regression, The system considers 350,899 records and 15 features, such as runs, wickets, overs, striker, and non-striker, based on Random Forest Regression and a Stacked Ensemble model. With 90.76% accuracy, the Random Forest model surpassed other approaches such as Support Vector Machines and Decision Trees. Statistical performance measures such as Mean Squared Error, Root Mean Squared Error, and R-Squared were employed to ensure the performance of the system. We point out the scope for extension to other forms of cricket, such as Test and T20 matches, and to other sports disciplines, although the present results may be used for ODI matches. Cloud computing is proposed to be incorporated into future enhancements for real-time predictive analytics and big data processing.