Mortality rate is the indicator of quantity of fatalities research. Since this is a worldwide issue, predicting rates as accurately as possible is important. Using machine learning regression is the most effective strategy to accomplish the goal mortality rates are continuous values, making regression an ideal method for analysis. We applied different regression models and found that Gradient Boosting and Random Forest Regressor performed the best. After applying grid search, each model’s performance improved. With an RMSE of 20.25, Random Forest, on the other hand, demonstrated the highest accuracy and most fitting to our data, demonstrating its overall high efficiency. Having an RMSE of 20.26, gradient boost showed superior results. Linear models like Linear, Ridge, Elastic Net, and Lasso showed similar results, with an RMSE of 20.88.KNN and Decision Tree performed less effectively, with KNN having an RMSE of 24.62 and Decision Tree having an RMSE of 24.51. SVR had the RMSE of 28.61. In conclusion, Random Forest provides the best accuracy, making regression model techniques appropriate for this problem statement.