To improve the utilization of open-pit mine resources and reduce operating costs, a study on truck fuel consumption prediction in open-pit mines was conducted. An Osprey Optimization Algorithm (OOA) was used to optimize the key hyperparameters of the Light Gradient Boosting Machine (LightGBM) model, and an OOA-LightGBM prediction model for truck fuel consumption in open-pit mines was established. This model comprehensively considers four main influencing factors: transport volume, transport distance, road quality, and slope. Using real-time truck operation data from a large open-pit mine in Shanxi Province, a simulation study was carried out. The simulation results show that, compared with traditional algorithms such as Support Vector Machine (SVM), the OOA-LightGBM model can predict truck fuel consumption more quickly and accurately. The model achieved a coefficient of determination (R2) of 0.9893, a mean squared error (MSE) of 0.1783, and a mean absolute error (MAE) of 0.2098, demonstrating its superiority and stability in fuel consumption prediction. This study provides robust technical support for mining enterprises to optimize transportation scheduling and reduce fuel consumption costs.