Skip to main content

Comparison of Traditional Econometric Models and Machine Learning Methods in the Context of Travel Decision Making and Perspectives for Synergy

  • 164 Accesses

Part of the Studies in Computational Intelligence book series (SCI,volume 990)

Abstract

The paper is motivated by a long-term recognition of the limitations of the traditional econometric methods such as logit choice model (on the one hand) and tremendous but still largely unutilized potential of the Machine Learning (ML) methods in transportation modeling (on the other hand). However, a simple replacement of logit models with ML methods proved to be problematic due to the specifics of transportation modeling domain. This stimulated the current research with the focus on ML adaptation to the transportation domain and possible hybridization with the traditional logit models. The main desired outcome of this research is moving ML methods as well as possible hybrid ML-econometrics methods into the core practice of transportation modeling.

Keywords

  • Decision making
  • Discrete choice
  • Machine learning
  • Econometrics

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-75583-6_18
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   169.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-75583-6
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   219.99
Price excludes VAT (USA)

References

  1. Li, V., Kockelman, K.M.: How does machine learning compare to conventional econometrics for transport data sets? A Test of ML vs. MLE. UTA white paper (2019)

    Google Scholar 

  2. Ben-Akiva, M., Lerman, S.R.: Discrete Choice Analysis: Theory and Application to Travel Demand. MIT Press, Cambridge (1985)

    Google Scholar 

  3. Basu, R., Ferreira, J.: Econometrics vs. machine learning: an application for predicting household vehicle ownership in Singapore. In: Presented at the 98th Annual Meeting of Transportation Research Board, Washington, DC (2019)

    Google Scholar 

  4. Garg, A., Noyola, J., Verma, R., Saxena, A., Jami, A.: Correlation based multi-label classification. Final Project – CS 221. Stanford University (2014)

    Google Scholar 

  5. Lee, D., Derrible, S., Pereira, F.C.: Comparison of four types of artificial neural networks and a multinomial logit model for travel mode choice modeling. In: Presented at the 97th Annual Meeting of Transportation Research Board, Washington, DC (2018)

    Google Scholar 

  6. Zhu, Z., Tang, L., Chan, X., Zhang, L.: travel mode choice decision making via bayesian decision network. In: Presented at the 95th Annual Meeting of Transportation Research Board, Washington, DC (2016)

    Google Scholar 

  7. Paredes, M., Hemberg, E., O’Reilly, U.-M., Zegras, C.: Machine learning or discrete choice models for car ownership demand estimation and prediction? IEEE Publication (2017)

    Google Scholar 

  8. Hagenauer, J., Helbich, M.: A comparative study of machine learning classifiers for modeling travel mode choice. Expert Syst. Appl. 78, 273–282 (2017)

    CrossRef  Google Scholar 

  9. Golshani N., Shabanopour, R., Mahmoudifard, S.M., Derrible, S., Mohammadian, A.: Comparison of artificial neural networks and statistical copula-based joint models. In: Presented at the 96th Annual Meeting of the Transportation Research Board, Washington, DC (2017)

    Google Scholar 

  10. van Cranenburgh, S., Kouwenhoven, M.: Using artificial neural networks for recovering the value-of-travel-time distribution. In: International Work-Conference on Artificial Neural Networks, pp. 88–102. Springer (2019)

    Google Scholar 

  11. Sifringer, B., Lurkin, V., Alahi, A.: Let me not lie: learning multinomial logit. arXiv:1812.09747v1 (2018)

  12. Aboutaleb, Y.M.: Learning structure in nested logit models. Master’s thesis, Massachusetts Institute of Technology (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Peter Vovsha .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Vovsha, P. (2021). Comparison of Traditional Econometric Models and Machine Learning Methods in the Context of Travel Decision Making and Perspectives for Synergy. In: Bucciarelli, E., Chen, SH., Corchado, J.M., Parra D., J. (eds) Decision Economics: Minds, Machines, and their Society. DECON 2020. Studies in Computational Intelligence, vol 990. Springer, Cham. https://doi.org/10.1007/978-3-030-75583-6_18

Download citation