<p>In recent years, engineered bamboo has gained attention for its potential use in sustainable construction, offering an alternative to traditional materials such as concrete and steel. However, the fracture behavior of engineered bamboo, particularly under Mode I loading conditions, remains underexplored, and reliable methods for predicting its critical load are scarce. This study aims to fill this gap by utilizing machine learning (ML) to predict the critical load for Mode I fracture in engineered bamboo. Three gradient-boosting models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost), were trained using a database that included key features such as specimen dimensions and material properties. Shapley additive explanations (SHAP) were employed to interpret the influence of each feature on the model predictions. The results reveal that specimen thickness is the most influential feature, while features such as tensile strength perpendicular to the grain and bending elastic modulus also contribute, though to a lesser extent. This study provides a data-driven approach for predicting the fracture behavior of engineered bamboo, offering valuable insights for the design and application of this material in structural engineering.</p>