Optimization is one of the factors in machine learning to help model training during backpropagation. This is conducted by adjusting the weights to minimize the loss function and to overcome dimensional problems. Also, the gradient descent method is a simple approach in the backpropagation model to solve minimum problems. The mini-batch gradient descent (MBGD) is one of the methods proven to be powerful for large-scale learning. The addition of several approaches to the MBGD such as AB, BN, and UR can accelerate the convergence process, hence, the algorithm becomes faster and more effective. This added method will perform an optimization process on the results of the data rule that has been processed as its objective function. The processing results showed the MBGD-AB-BN-UR method has a more stable computational time in the three data sets than the other methods. For the model evaluation, this research used RMSE, MAE, and MAPE.