Surface roughness imposes one of the most critical constraints for the selection of machine and cutting parameters in process planning. Therefore, the present research is focused on optimization of machining conditions of Al 1050/SiCp MMCs. The cutting conditions used in this research are; cutting speed, depth of cut, feed rate as well as volume fraction and particle size of the reinforcement. The experimental results collected are tested with analyses of variance (ANOVA), artificial neural network (ANN) and genetic algorithm (GA) techniques. Multilayer perception model has been constructed with back- propagation algorithm using the input parameters. Output parameter is surface roughness of the machined part. On completion of the experimental test, the three techniques are used to validate the obtained results and also to optimize the behavior of the system under cutting conditions within the machining range. From the analysis of the results, it can be seen that, this approach is more flexible when compared with other models developed based on the experimental results that constrain their applicability of selecting the process parameters from limited range. From the output data obtained through ANOVA, ANN and GA approaches, the optimum conditions are; cutting speed (112 and 140 rpm), depth of cut (1.0 and1.5 mm), feed rate(0.8 and 1.25  mm/rev), volume fraction( 10 and 25 %) and particle size(10 and 25µm). There is a close matching between the models outputs and the experimental results of surface roughness (Ra). ANOVA technique is more accurate than the two others techniques ANN and GA. In ANOVA outputs the deviation between model outputs and the experimental results of (Ra) is between 0.0 and 0.1.