Green buildings represent a promising solution for advancing high-quality development in the building sector to combat climate change. Selecting appropriate credits from the rating system based on the distinct characteristics of buildings is a crucial step in the green building certification process. However, in practice, credit selection is a complex and challenging task, often relying on the personal experience of experts. This study develops a model based on explainable machine learning techniques, aiming to aid architects in selecting suitable credits in the early stages of green building design and explore the impact of various factors on credit selection. A case library of 210 green buildings is established to verify the model's performance. The model demonstrated a notable precision rate of 82.38 % in the selection of regular credits. Leveraging SHapley Additive exPlanations (SHAP) technology, the model uncovers a pattern indicating that buildings sharing specific characteristics tend to exhibit similar performance on particular credits, suggesting an inherent preference or avoidance of these credits. The model developed in this study offers practical strategies for architects in credit selection, reducing the reliance on expert opinions and simplifying the credit selection process. The introduction of explainable machine learning techniques enhances the transparency of model decisions and provides targeted insights for architects and standard setters.