ABSTRACT
This paper explores the joint effects of economic development, demographic characteristics and road network on road safety. Although extensive efforts have been undertaken to model safety effects of various influential factors, little evidence is provided on the relative importance of explanatory variables by accounting for their mutual interactions and non-linear effects. We present an innovative gradient boosting decision tree (GBDT) model to explore joint effects of comprehensive factors on four traffic accident indicators (the number of traffic accidents, injuries, deaths, and the economic loss). A total of 27 elaborated influential factors in Zhongshan, China during 2000–2016 are collected. Results show that GBDT not only presents high prediction accuracy, but can also handle the multicollinearity between explanatory variables; more importantly, it can rank the influential factors on traffic accidents. We also investigate the partial effects of key influential factors. Based on key findings, we highlight the practical insights for planning practice.
Disclosure statement
No potential conflict of interest was reported by the authors.
ORCID
Ronghui Liu http://orcid.org/0000-0003-0627-3184