Abstarct: Estimating the Rate of Penetration (ROP) is one of the key factors in improving drilling efficiency and reducing operational costs. In this study, Support Vector Regression (SVR) was employed as an advanced machine learning technique to develop a predictive model for estimating the ROP in one of the oil fields in southern Iraq. The study was conducted using real field data collected from four oil wells. Data from Wells 1, 2, and 3 were used for model training and optimization, while the data from Well 4, which was not included in the training process, were utilized to evaluate the model's performance and its ability to predict unseen data. Prior to model development, several preprocessing steps were carried out, including data cleaning, outlier removal, and normalization, in order to improve the model's accuracy and stability. The results demonstrated that the SVR model was capable of effectively capturing the nonlinear relationships between drilling operational parameters and the rate of penetration. The model achieved a correlation coefficient (R) of approximately 0.95 for the training dataset and about 0.92 for the testing dataset. Furthermore, the relatively low values of the Average Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE) indicated the model's satisfactory accuracy in estimating the rate of penetration. baxsed on the obtained results, Support Vector Regression proved to be an efficient tool for predicting the rate of penetration in the studied formations, showing strong generalization capability and a high ability to model complex relationships among drilling variables. Therefore, the application of SVR can contribute significantly to improving engineering decision-making and enhancing drilling performance.