Advanced search
1 file | 1.89 MB Add to list

Applying an ensemble-based model to travel choice behavior in travel demand forecasting under uncertainties

Author
Organization
Abstract
The application of travel demand models to transportation planning has triggered great interests in issues that potentially improve the accuracy of model forecasts. These forecasts, however, are subject to various sources of input and model uncertainties. Focusing on travel choice behavior, this paper draws attention to the use of an ensemble-based model for addressing these uncertainties. A random multinomial logit (RMNL) model is developed by assembling a collection of multinomial logit (MNL) models. The bootstrapping procedure and the random feature selection are employed to capture the uncertainties in the model. A case study of investigating travel mode choice behaviors that illustrates situations necessitating the RMNL model is presented. Results suggest that the uncertainty related to predictions is reduced and the prediction accuracy is much improved. The RMNL model is computationally efficient and provides useful interpretations by estimating variable significance. Also, the RMNL model is able to deal with high-dimensional data.
Keywords
Transportation, ensemble-based model, travel mode choice, bootstrapping, random feature selection, input uncertainty, model uncertainty, DISCRETE-CHOICE, TRAFFIC FORECASTS, MIXED LOGIT, TIME, SYSTEM, RELIABILITY, SELECTION, IMPACT, CHAIN, STATE

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.89 MB

Citation

Please use this url to cite or link to this publication:

MLA
Cheng, Long, et al. “Applying an Ensemble-Based Model to Travel Choice Behavior in Travel Demand Forecasting under Uncertainties.” TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH, vol. 12, no. 6, 2020, pp. 375–85, doi:10.1080/19427867.2019.1603188.
APA
Cheng, L., Lai, X., Chen, X., Yang, S., De Vos, J., & Witlox, F. (2020). Applying an ensemble-based model to travel choice behavior in travel demand forecasting under uncertainties. TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH, 12(6), 375–385. https://doi.org/10.1080/19427867.2019.1603188
Chicago author-date
Cheng, Long, Xinjun Lai, Xuewu Chen, Shuo Yang, Jonas De Vos, and Frank Witlox. 2020. “Applying an Ensemble-Based Model to Travel Choice Behavior in Travel Demand Forecasting under Uncertainties.” TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH 12 (6): 375–85. https://doi.org/10.1080/19427867.2019.1603188.
Chicago author-date (all authors)
Cheng, Long, Xinjun Lai, Xuewu Chen, Shuo Yang, Jonas De Vos, and Frank Witlox. 2020. “Applying an Ensemble-Based Model to Travel Choice Behavior in Travel Demand Forecasting under Uncertainties.” TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH 12 (6): 375–385. doi:10.1080/19427867.2019.1603188.
Vancouver
1.
Cheng L, Lai X, Chen X, Yang S, De Vos J, Witlox F. Applying an ensemble-based model to travel choice behavior in travel demand forecasting under uncertainties. TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH. 2020;12(6):375–85.
IEEE
[1]
L. Cheng, X. Lai, X. Chen, S. Yang, J. De Vos, and F. Witlox, “Applying an ensemble-based model to travel choice behavior in travel demand forecasting under uncertainties,” TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH, vol. 12, no. 6, pp. 375–385, 2020.
@article{8624453,
  abstract     = {The application of travel demand models to transportation planning has triggered great interests in issues that potentially improve the accuracy of model forecasts. These forecasts, however, are subject to various sources of input and model uncertainties. Focusing on travel choice behavior, this paper draws attention to the use of an ensemble-based model for addressing these uncertainties. A random multinomial logit (RMNL) model is developed by assembling a collection of multinomial logit (MNL) models. The bootstrapping procedure and the random feature selection are employed to capture the uncertainties in the model. A case study of investigating travel mode choice behaviors that illustrates situations necessitating the RMNL model is presented. Results suggest that the uncertainty related to predictions is reduced and the prediction accuracy is much improved. The RMNL model is computationally efficient and provides useful interpretations by estimating variable significance. Also, the RMNL model is able to deal with high-dimensional data.},
  author       = {Cheng, Long and Lai, Xinjun and Chen, Xuewu and Yang, Shuo and De Vos, Jonas and Witlox, Frank},
  issn         = {1942-7867},
  journal      = {TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH},
  keywords     = {Transportation,ensemble-based model,travel mode choice,bootstrapping,random feature selection,input uncertainty,model uncertainty,DISCRETE-CHOICE,TRAFFIC FORECASTS,MIXED LOGIT,TIME,SYSTEM,RELIABILITY,SELECTION,IMPACT,CHAIN,STATE},
  language     = {eng},
  number       = {6},
  pages        = {375--385},
  title        = {Applying an ensemble-based model to travel choice behavior in travel demand forecasting under uncertainties},
  url          = {http://dx.doi.org/10.1080/19427867.2019.1603188},
  volume       = {12},
  year         = {2020},
}

Altmetric
View in Altmetric
Web of Science
Times cited: