刘锴 (教授)

教授   博士生导师   硕士生导师

性别:男

毕业院校:名古屋大学

学位:博士

所在单位:经济管理学院

学科:交通运输规划与管理. 交通信息工程及控制

办公地点:大连理工大学经济管理学院D435室

联系方式:+86-411-84706221

电子邮箱:liukai@dlut.edu.cn

当前位置: 中文主页 >> 科学研究 >> 论文成果

Key determinants and heterogeneous frailties in passenger loyalty toward customized buses: An empirical investigation of the subscription termination hazard of users

点击次数:

论文类型:期刊论文

发表时间:2020-06-01

发表刊物:TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES

收录刊物:SCIE、SSCI

卷号:115

ISSN号:0968-090X

关键字:Demand responsive bus; Subscription behavior; User loyalty; Demand evolution; Shared frailty model

摘要:Long-term passenger subscription is vital to the survival and operation of the customized bus (CB) system, which is a demand-driven and user-oriented transit service. A better understanding of passenger loyalty toward the CB service will help provide better operation. The urgent and outstanding issue is how to incorporate the unobserved heterogeneity in loyalty-in other words, how to reflect the effects of the frailty to terminate subscription. This study fills the research gap through an empirical study in Dalian, China. Three different survival models are developed to investigate the mechanism of subscription behaviors, among which the shared frailty model considering the unobserved heterogeneity is demonstrated to be the most appropriate. The results indicate that the historical purchase characteristics are the most important to CB user loyalty modeling and forecasting. Males are more sensitive than females to the number of intermediate stations because of the potentially increased uncertainty in waiting time related to the intermediate stations. The heterogenous frailties resulting from the heterogeneity of the perceptible service quality in terms of convenience and efficiency in subscribing/returning tickets and information availability in the progress of the CB system significantly contribute to user loyalty deviations.

发表时间:2020-06-01

上一条: Optimal Location of Fast Charging Stations for Mixed Traffic of Electric Vehicles and Gasoline Vehicles Subject to Elastic Demands

下一条: A deep learning method for travel demand predictions of dynamic internet based ride-sharing