Gas Metal Arc Welding (GMAW) is an extensively implemented arc welding process through the control of input process parameters and the metal from the filler wire. Despite its popular use in various industries, the complex interrelationship between the actual bead and the varying welding parameters makes it challenging to predict appropriate bead geometries via mathematical modeling in a continually changing welding process. In this study, the Regression Learner App was used to compare the performance of supervised Machine Learning (ML) predictive models comprising the Linear Regression (LR), Regression Tree (RT), Support Vector Machine (SVM), Ensembles of Tree (ET), Gaussian Process Regression (GPR), and Artificial Neural Network (ANN) using GMAW dataset. The dataset was scaled and normalized at a range of -1 to +1 to facilitate the visualization of the variation effect. The wire feed speed, voltage, weld velocity, unmelted wire length, and melted wire volume were considered as the input parameters to predict the bead geometry. In addition, the five-fold cross-validation was employed to avoid overfitting and poor generalization. Finally, statistical indicators, namely the Coefficient of Determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), were performed on all developed models to evaluate their performance. Thus, the fine tree and ANN models achieved the highest prediction accuracies of 88–91%, signifying their potential use in future research. In short, the present study demonstrated the performance of various supervised ML algorithms for bead geometry prediction, which would assist the selection of appropriately supervised ML algorithms in future studies.