In the present research, an Artificial Neural Network (ANN) model has been exhibited to investigate and, which could predict the variation of the overcut, in the electrical discharge machining (EDM) process on AISI D2 tool steel. In EDM process, the overcut significantly influences the precision and accuracy of the work piece dimensions. Since, the overcut and the final work piece dimensions are difficult to predict due to the non-linear, complex relationship between the electrode wear, the electrode diameter, electrical discharging parameters, and the machine positioning accuracy. The discharge current (Ip), pulse duration (Ton), duty fraction (Tau) and voltage (V) are considered as inputs for the network. A full factorial design was used to conduct the experiments with various levels of Ip, Ton, Tau and V. The three fourth of the experimental data set was used to train the network and was tested for convergence. The Mean Square Error (MSE) convergence criteria, both in training and testing, came out very well. The developed models are found to approximate the responses quite accurately. Moreover, the predicted results based on above models have been confirmed with unseen validation set of experiments and are found to be in good agreement with the experimental results. The comparison results reveal that the proposed models can be employed successfully in prediction of radial overcut of the stochastic and complex EDM process. © Nova Science Publishers, Inc.