The application of machine learning techniques in predicting wear properties of reinforced materials is a topic of significant interest in materials science and engineering. In this study, the application of linear regression and Artificial Neural Network (ANN) models is explored for predicting the friction coefficient (Fc) and specific rate of wear (Sr) of Al 7090 alloy reinforced with zirconium oxide nanoparticles. The alloy is prepared using the stir casting method, with varying percentages of ZrO2 nanoparticles. A comprehensive wear test is conducted using a pin-on-disc wear testing apparatus, where load (L), rotational speed (Rs), composition (C), and distance of sliding (Ds) are considered as input parameters. The experimental setup is optimized using the Taguchi design and L27 array. The accuracy of the linear regression and ANN models is evaluated by comparing the predicted responses with the observed values. The results demonstrate the efficacy of both linear regression and ANN models in accurately predicting the wear properties of the reinforced alloy. The linear regression model achieves an accuracy rate of 98.34%, while the ANN model surpasses it with an impressive accuracy rate of 99.94%. These findings highlight the potential of machine learning techniques in capturing the complex relationships between input variables and wear behavior.