Data-Driven Approach to Analyzing Factors Influencing Construction Accident Severity Using SHAP Analysis

Despite advances in construction safety research, existing studies face critical limitations, including severe data imbalance in accident severity classification and lack of interpretable machine-learning models for factor contribution analysis. This study addresses these gaps by combining extreme gradient boosting (XGBoost) with Shapley additive explanation (SHAP) analysis to quantitatively evaluate key factors influencing construction accident severity based on workday loss. Advanced oversampling techniques resolved class imbalance among severity levels (fatal, very serious, serious, and minor), while hyperparameter tuning optimized model performance. The analysis identified the top five factors influencing accident severity: original cause material (55.76), accident month (46.38), project scale (40.17), PET range (29.04), and age (21.53). The XGBoost-SHAP framework successfully demonstrated superior performance in accident prediction while providing interpretable factor contributions, validating workday loss as an effective severity quantification method. The findings enable risk assessment in large-scale projects and extreme environmental conditions, offering a scientific basis for developing targeted accident prevention strategies and optimizing safety resource allocations.