This study explores the use of machine learning (ML) to predict the corrosion inhibition efficiency (CIE) of pyrimidine compounds, which are promising, non-toxic, and cost-effective corrosion inhibitors. The researchers compared 14 linear and 12 non-linear ML algorithms using a quantitative structure-property relationship (QSPR) model. The bagging regressor model was found to be the most accurate, achieving a root mean square error (RMSE) of 5.38, a mean square error (MSE) of 28.93, a mean absolute error (MAE) of 4.23, and a mean absolute percentage error (MAPE) of 0.05. This research provides a novel and efficient ML-based approach to predicting CIE, offering a significant advancement in corrosion science and a practical solution for industries facing corrosion challenges. The study highlights the potential of machine learning to enhance corrosion control strategies by quickly and accurately determining the effectiveness of organic chemical inhibitors.This study explores the use of machine learning (ML) to predict the corrosion inhibition efficiency (CIE) of pyrimidine compounds, which are promising, non-toxic, and cost-effective corrosion inhibitors. The researchers compared 14 linear and 12 non-linear ML algorithms using a quantitative structure-property relationship (QSPR) model. The bagging regressor model was found to be the most accurate, achieving a root mean square error (RMSE) of 5.38, a mean square error (MSE) of 28.93, a mean absolute error (MAE) of 4.23, and a mean absolute percentage error (MAPE) of 0.05. This research provides a novel and efficient ML-based approach to predicting CIE, offering a significant advancement in corrosion science and a practical solution for industries facing corrosion challenges. The study highlights the potential of machine learning to enhance corrosion control strategies by quickly and accurately determining the effectiveness of organic chemical inhibitors.