Data-Driven Approach to Analyzing Factors Influencing Construction Accident Severity Using SHAP Analysis
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".