Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost

Manze Guo,Yang Yang,Yongxin Peng,Wencheng Wang,Zhenzhou Yuan,Bruce Janson

doi:10.3390/su13020926

Abstract

Older pedestrians are vulnerable on the streets and at significant risk of injury or death when involved in crashes. Pedestrians’ safety is critical for roadway agencies to consider and improve, especially older pedestrians aged greater than 65 years old. To better protect the older pedestrian group, the factors that contribute to the older crashes need to be analyzed deeply. Traditional modeling approaches such as Logistic models for data analysis may lead to modeling distortions due to the independence assumptions. In this study, Extreme Gradient Boosting (XGBoost), is used to model the classification problem of three different levels of severity of older pedestrian traffic crashes from crash data in Colorado, US. Further, Shapley Additive explanations (SHAP) are implemented to interpret the XGBoost model result and analyze each feature’s importance related to the levels of older pedestrian crashes. The interpretation results show that the driver characteristic, older pedestrian characteristics, and vehicle movement are the most important factors influencing the probability of the three different severity levels. Those results investigate each severity level’s correlation factors, which can inform the department of traffic management and the department of road infrastructure to protect older pedestrians by controlling or managing some of those significant features.

Highlights

With the continuous growth of the world’s population and the increasing complexity of road conditions, pedestrian traffic crashes remain high
A further interpretation of XGBoost model results such as permutation importance, partial dependence plots by Shapley Additive explanations (SHAP) is implemented in this study
The detailed generation of SHAP value is introduced in the methodology section

Summary

Introduction

With the continuous growth of the world’s population and the increasing complexity of road conditions, pedestrian traffic crashes remain high. International crashes statistics indicates that older pedestrian is an extremely vulnerable group on the road [1]. In the United States, pedestrians’ fatality rate has increased by more than 3% from 1990 to 2018. In the United States, the 2017 data show that the population over 65 only accounts for 15.42%, while the death rate of road pedestrian crashes over 65 is as high as 19.7%, an increase of 8.4 percentage points compared with the 1985 data. NHTSA’s National Pedestrian Crash Report’s statistical results show that Pedestrian fatalities declined between 1997 and 2006. It is found that the older age group (over 64) has a much greater possibility than other age groups

Methods

Results

Discussion

Conclusion