Modeling driving styles of online ride-hailing drivers with model identifiability and interpretability

被引:7
作者
Ma, Yongfeng [1 ,2 ]
Xie, Zhuopeng [1 ,2 ]
Li, Wenlu [1 ,2 ]
Chen, Shuyan [1 ,2 ]
机构
[1] Southeast Univ, Sch Transportat, Jiangsu Key Lab Urban ITS, Nanjing 211189, Peoples R China
[2] Southeast Univ, Jiangsu Prov Collaborat Innovat Ctr Modem Urban Tr, Nanjing 211189, Peoples R China
基金
中国国家自然科学基金;
关键词
Online ride-hailing; Driving style; Interpretable machine learning; CatBoost; Shapley additive explanation; BEHAVIOR; PERSONALITY; IDENTIFICATION; SMARTPHONES; PLATFORM; DEFINE; SYSTEM; SPEED;
D O I
10.1016/j.tbs.2023.100645
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
The online ride-hailing industry has grown rapidly and has greatly improved travel efficiency worldwide. The driving styles of the drivers of ride-hailing vehicles largely determine the safety and comfort of passengers. Therefore, identifying and analyzing such driving styles are important tasks in order to maintain travel safety and efficiency. However, few studies have focused specifically on online ride-hailing drivers' driving styles, and those few usually suffer from a lack of representativeness of influential factors as well as from failure to balance the identification accuracy and interpretability of the model applied. To address these issues, we propose an interpretable machine learning method to model the driving styles of online ride-hailing drivers. The proposed method considers both model identifiability and interpretability. First, we conducted naturalistic driving tests in Nanjing, China to collect driver data, vehicle kinematic data, and video data. Then, we extracted driver features, environmental features, and online ride-hailing driving features as the influential factors. Next, we used the CatBoost algorithm to identify three types of driving styles: aggressive, normal, and cautious. Finally, we used the Shapley additive explanation (SHAP) algorithm (1) to explore the effects of the influential factors on the driving styles from four perspectives (feature importance, total effect, main effect, and interaction effect) and (2) to analyze the differences in driving styles between online ride-hailing drivers and ordinary drivers. In addition, to verify the effectiveness of CatBoost, we compared it to three typical machine learning algorithms: extreme gradient boosting (XGBoost), artificial neural network, and support vector machine. The results show that CatBoost significantly outperformed the other three algorithms with macro-average precision, recall, and F1score values of 0.818, 0.881, and 0.842, respectively. Also, SHAP was able to explain the complex nonlinear relationship between the driving styles and the influential factors. Overall, the distance, driving event, driver age, driving task, and duration features are of relatively high importance. This study provides an effective and innovative method to identify and analyze the driving styles of online ride-hailing drivers. Importantly, this method can help the online ride-hailing industry to monitor, analyze, and improve drivers' driving behavior and thus improve travel safety and efficiency.
引用
收藏
页数:21
相关论文
共 64 条
  • [31] Characterization of ridesplitting based on observed data: A case study of Chengdu, China
    Li, Wenxiang
    Pu, Ziyuan
    Li, Ye
    Ban, Xuegang
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2019, 100 : 330 - 353
  • [32] Predicting driver drowsiness using vehicle measures: Recent insights and future challenges
    Liu, Charles C.
    Hosking, Simon G.
    Lenne, Michael G.
    [J]. JOURNAL OF SAFETY RESEARCH, 2009, 40 (04) : 239 - 245
  • [33] The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver's Driving Style: A Case Study in China
    Liu, Runkun
    Yu, Haiyang
    Ren, Yilong
    Liu, Shuai
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2022, 19 (15)
  • [34] A Semi-Supervised Tri-CatBoost Method for Driving Style Recognition
    Liu, Weirong
    Deng, Kunyuan
    Zhang, Xiaoyong
    Cheng, Yijun
    Zheng, Zhiyong
    Jiang, Fu
    Peng, Jun
    [J]. SYMMETRY-BASEL, 2020, 12 (03):
  • [35] Lundberg SM, 2017, ADV NEUR IN, V30
  • [36] Using naturalistic driving data to identify driving style based on longitudinal driving operation conditions
    Lyu N.
    Wang Y.
    Wu C.
    Peng L.
    Thomas A.F.
    [J]. Journal of Intelligent and Connected Vehicles, 2022, 5 (01): : 17 - 35
  • [37] The Impact of Aggressive Driving Behavior on Driver-Injury Severity at Highway-Rail Grade Crossings Accidents
    Ma, Changxi
    Hao, Wei
    Xiang, Wang
    Yan, Wei
    [J]. JOURNAL OF ADVANCED TRANSPORTATION, 2018,
  • [38] Real-time detection of abnormal driving behavior based on long short-term memory network and regression residuals
    Ma, Yongfeng
    Xie, Zhuopeng
    Chen, Shuyan
    Qiao, Fengxiang
    Li, Zeyang
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2023, 146
  • [39] Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry
    Ma, Yongfeng
    Li, Wenlu
    Tang, Kun
    Zhang, Ziyu
    Chen, Shuyan
    [J]. ACCIDENT ANALYSIS AND PREVENTION, 2021, 154
  • [40] On-line aggressive driving identification based on in-vehicle kinematic parameters under naturalistic driving conditions
    Ma, Yongfeng
    Tang, Kun
    Chen, Shuyan
    Khattak, Aemal J.
    Pan, Yingjiu
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2020, 114 : 554 - 571