For the Resistance Spot Welding (RSW) Process, the effects of Welding Current (WC), Electrode Force (EF), Welding Cycle (WCY), and Cooling Cycle (CCY) on the Tensile-Shear Strength (TSS) of the joints have been experimentally investigated. An Adaptive Neural-Fuzzy Inference System (ANFIS) based on data taken from the test results were developed for modelling and predicting of TSS of welds. Optimal parameters of ANFIS system were extracted by Gray Wolf Optimization (GWO) algorithm. The results show that ANFIS network can successfully predict the TSS of RSW welded joints. It can be concluded that the coefficient of determination and mean absolute percentage error for the test section data is 0.97 and 2.45% respectively, which indicates the high accuracy of the final model in approximating the desired outputs of the Process. After modeling with ANFIS-GWO, the effect of each input parameter on TSS of the joints was quantitatively measured using Sobol sensitivity analysis method. The results show that increasing in WC, WCY, EF, and CCY leads to an increase in TSS of joints.