The objective of this work is to highlight the modeling capabilities of artificial intelligence techniques for predicting the machining force during endmilling of GFRP composites. The present scenario demands such types of models to investigate the influence of the milling parameters on the thrust force during milling operation. In order to predict the performance of the input parameters (feed rate, speed, fibre orientation and depth of cut) and their interactions, detailed experiments were conducted based on the Response Surface Methodology (RSM) and the influences on the thrust force was assessed. The results indicated that the feed rate is the cutting parameter which has greater influence on Machining force for GFRP composite materials, followed by the cutting speed. The developed second order response surface model was validated using confirmation test and the error was found to be within ±0.3%. A Back Propagation (BP) model in Artificial Neural Networks (ANN) was developed. The developed ANN model was compared with the RSM models for the prediction of machining force of milled GFRP composites.