Based on the interpretable Machine learning algorithm gradient boosting machine (GBM), this study employs the long-term pavement performance (LTPP) database to predict the rut depth of asphalt pavement by considering various influential factors, including environmental, traffic, structural, and material variables. Compared with artificial neural network (ANN) and support vector machines (SVM), the GBM model provides superior interpretability by explaining the partial dependence of key factors. The results show that, compared with ANN and SVM, the GBM model reduces the RMSE by 0.75 and 0.25, and the MAE by 0.54 and 0.07, respectively, on the test datasets. The main factors affecting rut depth include the initial rutting depth measurement, time elapsed since the first measurement, total asphalt pavement thickness, and cumulative equivalent single axle load (ESAL). The partial dependency analysis helps pavement maintenance departments better understand rutting development under various influential factors, thereby supporting more effective pavement maintenance and management decisions.