The effect of machining parameters on the surface finish of medium carbon steel during turning operation on the lathe machine was thoroughly investigated using an artificial neural network (ANN). This study utilized data from a previous study on the effect of machining parameters on the surface roughness of medium carbon steel using a lathe machine. In this analysis, the neural network toolbox of MATLAB 2015 was used to predict the surface roughness of steel. In the MATLAB software, the dataset was partitioned into three sets: the training (70%), test (15%), and validation (15%) sets. The training data are used to adjust the weight of the neurons, the validation data are used to ensure the generalization of the network during the training stage, and the testing data are used to examine the network after being finalized. The stopping criteria are usually determined by pre-set error indices (such as mean square error, MSE) or when the number of epochs reaches 1000 (default setting). However, the number of epochs was set at 1000 for this study. The result revealed that the predicted model of the 3-10-1 architecture network fits the actual values for both training, testing, and validation sets well, as can be seen in their correlation coefficients (R²) of 0.9992, 0.9897, and 0.9765 for the training, testing, and validation data, respectively. Notably, a large sensitivity to a parameter shows that the system’s performance can drastically change with a small variation in the parameter and vice versa. Following this analogy, the process input variable, namely, the feed rate, has the highest impact on the surface roughness of steel, followed by the cutting speed and then the cut depth. Finally, the effect of machining parameters on the surface finish of medium carbon steel during turning operation on the lathe machine was successfully determined using ANN.