In traditional studies on grassland degradation drivers, researchers often lacked the flexibility to selectively consider driving factors and quantitatively depict their contributions. Interpretable machine learning offers a solution to these challenges. This study focuses on Inner Mongolia, China, incorporating four categories and sixteen specific driving factors, and employing four machine learning techniques (Logistic Regression, Random Forest, XGBoost, and LightGBM) to investigate regional grassland changes. Using the SHAP approach, contributions of driving factors were quantitatively analyzed. The findings reveal the following: (1) Between 2015 and 2020, Inner Mongolia experienced significant grassland degradation, with an affected area reaching 12.12 thousand square kilometers. (2) Among the machine learning models tested, the LightGBM model exhibited superior prediction accuracy (0.89), capability (0.9), and stability (0.76). (3) Key factors driving grassland changes in Inner Mongolia include variations in rural population, livestock numbers, average temperatures during the growth season, peak temperatures, and proximity to roads. (4) In eastern and western Inner Mongolia, changes in rural population (31.4%) are the primary degradation drivers; in the central region, livestock number changes (41.1%) dominate; and in the southeast, climate changes (19.3%) are paramount. This work exemplifies the robust utility of interpretable machine learning in predicting grassland degradation and offers insights for policymakers and similar ecological regions.