Predicting Future Driving Risk of Crash-Involved Drivers Based on a Systematic Machine Learning Framework.

Chen Wang,Lin Liu,Weitao Lv,Chengcheng Xu

doi:10.3390/ijerph16030334

Abstract

The objective of this paper is to predict the future driving risk of crash-involved drivers in Kunshan, China. A systematic machine learning framework is proposed to deal with three critical technical issues: 1. defining driving risk; 2. developing risky driving factors; 3. developing a reliable and explicable machine learning model. High-risk (HR) and low-risk (LR) drivers were defined by five different scenarios. A number of features were extracted from seven-year crash/violation records. Drivers’ two-year prior crash/violation information was used to predict their driving risk in the subsequent two years. Using a one-year rolling time window, prediction models were developed for four consecutive time periods: 2013–2014, 2014–2015, 2015–2016, and 2016–2017. Four tree-based ensemble learning techniques were attempted, including random forest (RF), Adaboost with decision tree, gradient boosting decision tree (GBDT), and extreme gradient boosting decision tree (XGboost). A temporal transferability test and a follow-up study were applied to validate the trained models. The best scenario defining driving risk was multi-dimensional, encompassing crash recurrence, severity, and fault commitment. GBDT appeared to be the best model choice across all time periods, with an acceptable average precision (AP) of 0.68 on the most recent datasets (i.e., 2016–2017). Seven of nine top features were related to risky driving behaviors, which presented non-linear relationships with driving risk. Model transferability held within relatively short time intervals (1–2 years). Appropriate risk definition, complicated violation/crash features, and advanced machine learning techniques need to be considered for risk prediction task. The proposed machine learning approach is promising, so that safety interventions can be launched more effectively.

Highlights

Since 2018, the Kunshan Traffic Police Department in China has been developing a comprehensive safety improvement plan, aiming to control the increasing numbers of crashes
The policy-makers intended to focus on specific driver groups with high driving risk instead of all registered drivers
Drivers with prior crash involvement were considered as a starting point, since they were often considered at-risk and had been largely examined by previous literature [1,2,3]

Summary

Introduction

Since 2018, the Kunshan Traffic Police Department in China has been developing a comprehensive safety improvement plan, aiming to control the increasing numbers of crashes. The policy-makers intended to focus on specific driver groups with high driving risk instead of all registered drivers. Drivers with prior crash involvement were considered as a starting point, since they were often considered at-risk and had been largely examined by previous literature [1,2,3]. The driving risk of those drivers was expected to be accurately predicted for a future short time period (e.g., one or two years). Safety interventions can be implemented in a more effective and efficient way. Res. Public Health 2019, 16, 334; doi:10.3390/ijerph16030334 www.mdpi.com/journal/ijerph

Objectives

Findings

Discussion

Conclusion