In the current work, the AZ91 hybrid composites are fabricated through the utilization of the stir casting technique, incorporating aluminum oxide (Al2O3) and graphene (Gr) as reinforcing elements. Wear behavior of the AZ91/Gr/ Al2O3 composites was examined with pin-on-disc setup under dry conditions. In this study, the variables of reinforcement percentage (R), load (L), velocity (V), and sliding distance (D) have been chosen to investigate their impact on the WR and COF. This study utilizes a full factorial design to conduct experiments. The experimental data was critical analyzed to examine the impact of each wear parameter (i.e. R, L, V and D) on the WR and COF of composites. The wear mechanisms at the extreme situations of maximum and lowest wear rates are also investigated by utilizing the SEM images of specimen's surface. The SEM study revealed the presence of delamination, abrasion, oxidation and adhesion mechanisms on the surface experiencing wear. Machine learning (ML) models, such as decision tree (DT), random forest (RF), and gradient boosting regression (GBR), are employed to create a robust prediction model for predicting output responses based on input variables. The experimental data trained and tested with 95% and 5% experimental data points respectively. It was noticed that among all the models the GBR model exhibited superior performance in predicting WR, with MSE = 0.0398, RMSE = 0.1996, MAE = 0.1673, and R2 = 98.89, surpassing the accuracy of other models.