This research investigates the effect of adding graphene oxide to Al 6061 alloy to improve the wear and friction characteristics of the resulting metal matrix composite. Three different weight percentages of graphene oxide (1%, 3%, and 5%) were supplementary to the alloy using the stir casting process, and the resulting materials were tested for rate of wear and its coefficient. The investigational outcomes were then augmented using signal-to-noise ratio investigation to identify the optimal combination of input parameters. Additionally, a regression analysis and an artificial neural network (ANN) were used to forecast the outputs. The ANN model achieved an accuracy of 99.87% in predicting the responses. The results presented that the adding of graphene oxide improved the wear resistance and reduced the friction coefficient of the composite, with the optimal combination of input parameters being a composition of 5%, a load of 40 N, a speed of 180 rpm, and a distance of sliding of 35 m. The regression analysis and ANN were both able to accurately predict the responses, with the ANN performing slightly better than the regression analysis. Overall, this research demonstrates the potential for using graphene oxide as a reinforcement material to recover the resistance and wear possessions of metal matrix composites, and highlights the usefulness of machine learning techniques in predicting and optimizing these properties.