Integrating probabilistic tensor factorization with Bayesian supervised learning for dynamic ridesharing pattern analysis

被引:16
作者
Zhu, Zheng [1 ]
Sun, Lijun [2 ]
Chen, Xiqun [3 ,4 ]
Yang, Hai [1 ]
机构
[1] Hong Kong Univ Sci & Technol, Dept Civil & Environm Engn, Kowloon, Hong Kong, Peoples R China
[2] McGill Univ, Dept Civil Engn & Appl Mech, Montreal, PQ, Canada
[3] Zhejiang Univ, Coll Civil Engn & Architecture, Hangzhou, Peoples R China
[4] Alibaba Zhejiang Univ Joint Res Inst Frontier Tec, Hangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
Ridesharing; Classification; Supervised learning; Tensor factorization; Latent class analysis; DEMAND RIDE SERVICES; TRAVEL MODE CHOICE; BEHAVIOR; OPTIMIZATION; PREDICTION; MANAGEMENT; IMPUTATION; CARPOOL;
D O I
10.1016/j.trc.2020.102916
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
In the era of transportation big data, the analysis of mobility patterns generally involves large quantities of datasets with high-dimensional variables recording individual travelers' activities and socio-economic attributes, bringing new challenges to researchers. Conventional regression-based models commonly require complex structures in depicting random or fixed effects with a considerable number of parameters to estimate, and state-of-the-art machine learning models are regarded as black-boxes that are not clear in interpreting the mechanism in human mobility. To overcome the challenges of capturing complex high-order relationships among variables of interest, this paper proposes a Bayesian supervised learning tensor factorization (BSTF) model for the classification of travel choices in the mobility pattern analysis. The BSTF model induces a hierarchical probabilistic structure between predictor variables and the dependent variable, which offers a nature supervised learning foundation via Bayesian inference. Latent class (LC) variables are considered in the BSTF model to discover hidden preferences/states among travelers associated with their mobility patterns. We apply the BSTF model to analyze passenger-side choice patterns between diverse service options on a ride-sourcing platform, drawing increasing attention during recent years. A case study with a real-world dynamic ridesharing dataset in Hangzhou, China, is conducted. Different cases of training sizes are utilized to fit the proposed BSTF model as well as some other state-of-the-art machine learning models. By identifying significant variables and derive their probabilistic relationship between service types (i.e., ridesharing, non-sharing, and taxi), the proposed BSTF model offers good performance in both classification accuracy and the interpretability of shared mobility.
引用
收藏
页数:20
相关论文
共 67 条
  • [1] Optimization for dynamic ride-sharing: A review
    Agatz, Niels
    Erera, Alan
    Savelsbergh, Martin
    Wang, Xing
    [J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2012, 223 (02) : 295 - 303
  • [2] A tour-based model of travel mode choice
    Miller, EJ
    Roorda, MJ
    Carrasco, JA
    [J]. TRANSPORTATION, 2005, 32 (04) : 399 - 422
  • [3] Ben-Akiva M., 1985, MIT Press Series in Transportation Studies, V1, P59
  • [4] A new flexible multiple discrete-continuous extreme value (MDCEV) choice model
    Bhat, Chandra R.
    [J]. TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2018, 110 : 261 - 279
  • [5] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [6] Cardie C., 2018, P ASME 2018 PRESS B, DOI DOI 10.1115/PVP2018-84176
  • [7] Ridesharing in North America: Past, Present, and Future
    Chan, Nelson D.
    Shaheen, Susan A.
    [J]. TRANSPORT REVIEWS, 2012, 32 (01) : 93 - 112
  • [8] LIBSVM: A Library for Support Vector Machines
    Chang, Chih-Chung
    Lin, Chih-Jen
    [J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
  • [9] A nonconvex low-rank tensor completion model for spatiotemporal traffic data imputation
    Chen, Xinyu
    Yang, Jinming
    Sun, Lijun
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2020, 117
  • [10] Missing traffic data imputation and pattern discovery with a Bayesian augmented tensor factorization model
    Chen, Xinyu
    He, Zhaocheng
    Chen, Yixian
    Lu, Yuhuan
    Wang, Jiawei
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2019, 104 : 66 - 77