Abstarct: Drilling is one of the most costly and critical processes in the oil and gas industry, and its optimization, particularly reducing bit wear rate, plays a key role in enhancing efficiency and lowering operational costs. Bit wear is influenced by a complex combination of geological and operational parameters, making its accurate modeling challenging. This research aims to develop an efficient predictive model for bit wear rate, focusing on the impact of geomechanical formation parameters. In this study, one-dimensional geomechanical modeling was initially performed using drilling data and petrophysical logs. This modeling enabled the extraction and calculation of key geomechanical parameters such as in-situ stresses, elastic moduli, formation compressive strength, pore pressure, and confined compressive strength. These parameters, representing the mechanical properties of rocks at depth, were considered as essential inputs for machine learning models. To accurately predict bit wear rate, advanced machine learning methods including Artificial Neural Networks, Random Forest, and the XGBOOST algorithm were employed. These algorithms were chosen due to their ability to identify complex and nonlinear patterns in data, suitable for modeling the relationships between geomechanical parameters and bit wear rate. The performance of the models was evaluated using standard criteria, and the results demonstrate the capability of these methods in predicting bit wear. The findings of this research provide a deeper understanding of the impact of geomechanical parameters on bit wear rate and offer a practical model for accurate prediction. This model can assist drilling engineers in optimizing operational parameters, selecting more effective bits, reducing unscheduled downtime, and ultimately significantly lowering drilling costs.