Table 1 Summary.

¹¹

Linear Regression, Logistic Regression, Naive Bayes, SVM, Decision Tree, Random Forest

Predictive modelling

Enhanced accuracy in predicting cricket scores and player roles

¹²

Supervised Machine Learning, SHAP Scores

Dynamic prediction of match outcomes with real-time feature importance analysis

Accuracy increased from 55% to 85% throughout the match, valuable for real-time decision-making

¹³

Naive Bayes, Logistic Regression, SVM

In-game predictions at various stages using LASSO for feature selection

Prediction accuracy ranged from 53.08% to 97.65% depending on the match stage; introduced strategy generator

¹⁴

XGBoost, Lasso, Ridge Regression

Historical data analysis with feature engineering for first innings score prediction

Improved accuracy in first innings score prediction, aiding in target-setting strategies

¹⁵

Gradient Boosting, Regression Tree, Bagging, Random Forest, BART

Analysis of contextual factors using tree-based models and interpretable ML methods

Identified key contextual factors affecting performance; provided strategies for pre-match and pre-season decisions