Comparing fatal crash risk factors by age and crash type by using machine learning techniques

Abstract

This study aims to use machine learning methods to examine the causative factors of significant crashes, focusing on accident type and driver's age. In this study, a wide-ranging data set from Jeddah city is employed to look into various factors, such as whether the driver was male or female, where the vehicle was situated, the prevailing weather conditions, and the efficiency of four machine learning algorithms, specifically XGBoost, Catboost, LightGBM and RandomForest. The results show that the XGBoost Model (accuracy of 95.4%), the CatBoost model (94% accuracy), and the LightGBM model (94.9% accuracy) were superior to the random forest model with 89.1% accuracy. It is worth noting that the LightGBM had the highest accuracy of all models. This shows various subtle changes in models, illustrating the need for more analyses while assessing vehicle accidents. Machine learning is also a transforming tool in traffic safety analysis while providing vital guidelines for developing accurate traffic safety regulations.

Fig 1. Distribution of driver age peaks in the 20–50-year range.

Fig 2. Accidents by crash type.

Fig 3. Accidents in different weather conditions.

Fig 4. Correlation heatmap between variable.

Fig 5. Methodology flow chart.

Fig 6. Confusion matrix for LightGBM model.

Fig 7. Confusion matrix for the XGBoost model.

Fig 8. Confusion matrix for CatBoost model.

Fig 9. Confusion matrix of random forest model.

Fig 10. Summary plot for the binary model.

Fig 11. Feature importance summary plot.

Fig 12. Feature importance bar chart.

Fig 13. SHAP value for fatal injuries.

Fig 14. SHAP value for non-fatal injuries.