This paper reports on the optimization and prediction of the surface roughness and cutting force in the turning of UHMWPE (ultra-high molecular weight polyethylene). To identify the controllable factors in turning UHMWPE, that can minimize the variation of the surface roughness and cutting force, a three-level full factorial design, considering the feed rate, depth of cut, and cutting speed was conducted. The Taguchi method and Response Surface Methodology (RSM) were employed for establishing a relationship between the input and output parameters, whereas the significance of each parameter was analyzed using the Analysis of Variance (ANOVA). A four-layer Artificial Neural Network (ANN) model with a back-propagation algorithm and a sigmoidal transfer function and two hidden layers was developed for simultaneous prediction of surface roughness and cutting force. The results of the ANOVA of the surface roughness indicated that the feed rate is the dominant parameter followed by cutting speed and depth of cut, whereas the main cutting force is significantly affected by all three cutting parameters. The advantage of the ANN over the RSM is that the former can be used to simultaneously predict the surface roughness and cutting force, providing the most accurate estimates of the surface roughness and cutting force.