In this study, Al7075 metal matrix composites are processed using the casting method, adding carbon nano tubes (CNT) as reinforcement material. The wear behavior of the Al7075/CNT composites was investigated using a pin-on-disc setup under dry conditions. Key factors such as reinforcement percentage, normal load, sliding velocity, and sliding distance were selected to assess their effects on wear rate and coefficient of friction. A set of 108 experiments were employed. The experimental data were carefully analyzed to understand the influence of each wear parameter on output responses. Additionally, the wear mechanisms under extreme conditions were studied using scanning electron microscope images of the specimen worn-surface. Scanning Electron Microscope analysis observed the existence of delamination, abrasion, oxidation, and adhesion as the main wear mechanisms. Machine learning models for WR were successfully developed using polynomial regression (PR), random forest (RF), support vector regression (SVR), and multi layer perceptron (MLP) algorithms. Among these, the SVR model demonstrated superior performance, achieving an RMSE of 0.1611 and an R2 of 98.76% indicating the highest predictive accuracy. Whereas, In COF prediction the RF model demonstrated superior accuracy with an RMSE of 0.0128 and an R2 of 98.71%, outperforming other models.