Machining SKD11 alloy, renowned for its impressive strength, presents a unique challenge in face milling. Traditional methods struggle to determine the individual influence of each cutting parameter (local cutting mode) on machining performance, such as surface roughness (Ra) and cutting force (Fc). This study explores the potential of Light Gradient Boosting Machine (LightGBM), a powerful machine learning technique, to model and predict these machining performance metrics. The model's predictive ability will be evaluated using metrics like RMSE and R2. By analyzing data on cutting parameters like feed rate (fz), cutting speed (Vc), axial depth of cut (ap), and radial depth of cut (ae), the LightGBM model aims to predict both Ra and Fc with exceptional accuracy. Shapley Additive exPlanations (SHAP) play a crucial role in interpreting the LightGBM model. It reveals how each parameter influences Ra and Fc during milling. The significance of this research lies in empowering manufacturers to understand the magnitude of each parameter's impact on machining performance. This knowledge allows them to adjust cutting parameters accordingly for optimal results.