Bending is one of the widely used forming processes for sheet metals. However, due to the metal elasticity, the springback characteristic is unavoidable, leading to deviations from the desired final shapes and causing cumulative fitting problems in the assembly stages. Thus, precise predictions of the springback responses will enhance the sheet metal forming and the overall manufacturing processes. This is achieved by employing tree-based machine learning algorithms. These algorithms are used for their simplicity, preciseness, and consistency. Based on the tree-based algorithms, many prediction models are constructed and evaluated. First, experimental setup is established to measure the springback angles for different manufacturing conditions such as: the bending angle, the sheet metal’s width and thickness, the machine settings, etc. Then, these data sets are divided into training and testing groups for the prediction models. This division is carried randomly, where 90% of the data sets are used for training, and 10% are left for testing the models’ accuracy. The models are evaluated by comparing their predicted springback angles with the experimental values. The deviation errors are measured using the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE). It isrevealed that the LightGBM prediction model is the most accurate model with 0.42 deg., 0.26 deg., and 0.52 deg. for MAE, MSE, and RMSE, respectively. The Gradient boosting comes in the second place with 0.66 deg., 0.760 deg., and 0.80 deg. for MAE, MSE, and RMSE, respectively.