The severe abrasive wear of the current cemented tungsten carbide (WC) tools is a "bottleneck" that limits the usage of machinery in hard rock mines. To address this issue, a revolutionary thermally stable diamond composite (TSDC) based cutting tool, also called Super Material Abrasive Resistant Tool (SMART*CUT) was developed by CSIRO. Before this novel tool is employed for practical rock cutting, the effects of the cutting parameters on the performance of the SMART*CUT picks must be determined and the cutting forces of the picks have to be estimated as they directly affect the capability and efficiency of the selected cutterhead and hence the excavation machine. In this study, rock cutting tests based on Taguchi's L25 orthogonal array were conducted to analyze the cutting parameters. The signal-to-noise (S/N) ratios and the analysis of variance (ANOVA) were applied to investigate the effects of depth of cut, attack angle, spacing and cutting speed on mean cutting and normal forces during the rock cutting process. Empirical models for predicting the cutting forces on SMART*CUT picks were developed using multiple linear regression (MLR) and artificial neural network (ANN) techniques. Parametric combinations for minimizing the cutting forces and the statistical significance of process factors were successfully determined by using the Taguchi technique. Good prediction capabilities with acceptable errors were achieved by the developed MLR and ANN models. However, the ANN models offered better accuracy and less deviation.