IDEAS home Printed from https://ideas.repec.org/a/eee/eejocm/v37y2020ics1755534520300348.html
   My bibliography  Save this article

Multitask learning deep neural networks to combine revealed and stated preference data

Author

Listed:
  • Wang, Shenhao
  • Wang, Qingyi
  • Zhao, Jinhua

Abstract

It is an enduring question how to combine revealed preference (RP) and stated preference (SP) data to analyze individual choices. While the nested logit (NL) model is the classical way to address the question, this study presents multitask learning deep neural networks (MTLDNNs) as an alternative framework, and discusses its theoretical foundation, empirical performance, and behavioral intuition. We first demonstrate that the MTLDNNs are theoretically more general than the NL models because of MTLDNNs’ automatic feature learning, flexible regularizations, and diverse architectures. By analyzing the adoption of autonomous vehicles (AVs), we illustrate that the MTLDNNs outperform the NL models in terms of prediction accuracy but underperform in terms of cross-entropy losses. To interpret the MTLDNNs, we compute the elasticities and visualize the relationship between choice probabilities and input variables. The MTLDNNs reveal that AVs mainly substitute driving and ride hailing, and that the variables specific to AVs are more important than the socio-economic variables in determining AV adoption. Overall, this work demonstrates that MTLDNNs are theoretically appealing in leveraging the information shared by RP and SP and capable of revealing meaningful behavioral patterns, although its performance gain over the classical NL model is still limited. To improve upon this work, future studies can investigate the inconsistency between prediction accuracy and cross-entropy losses, novel MTLDNN architectures, regularization design for the RP-SP question, MTLDNN applications to other choice scenarios, and deeper theoretical connections between choice models and the MTLDNN framework.

Suggested Citation

  • Wang, Shenhao & Wang, Qingyi & Zhao, Jinhua, 2020. "Multitask learning deep neural networks to combine revealed and stated preference data," Journal of choice modelling, Elsevier, vol. 37(C).
  • Handle: RePEc:eee:eejocm:v:37:y:2020:i:c:s1755534520300348
    DOI: 10.1016/j.jocm.2020.100236
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1755534520300348
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.jocm.2020.100236?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Patricia K. Lyon, 1984. "Time-Dependent Structural Equations Modeling: A Methodology for Analyzing the Dynamic Attitude-Behavior Relationship," Transportation Science, INFORMS, vol. 18(4), pages 395-414, November.
    2. Yann LeCun & Yoshua Bengio & Geoffrey Hinton, 2015. "Deep learning," Nature, Nature, vol. 521(7553), pages 436-444, May.
    3. Golob, Thomas F. & McNally, Michael G., 1997. "A Model of Activity Participation Between Household Heads," University of California Transportation Center, Working Papers qt4dj8f1gg, University of California Transportation Center.
    4. Golob, Thomas F. & Bunch, David S. & Brownstone, David, 1997. "A Vehicle Use Forecasting Model Based on Revealed and Stated Vehicle Type Choice and Utilisation Data," University of California Transportation Center, Working Papers qt2x86k20c, University of California Transportation Center.
    5. Jerry Hausman, 2001. "Mismeasured Variables in Econometric Analysis: Problems from the Right and Problems from the Left," Journal of Economic Perspectives, American Economic Association, vol. 15(4), pages 57-67, Fall.
    6. Golob, Thomas F., 2003. "Structural equation modeling for travel behavior research," Transportation Research Part B: Methodological, Elsevier, vol. 37(1), pages 1-25, January.
    7. Golob, Thomas F & Bunch, David S & Brownstone, David, 1997. "A Vehicle Use Forecasting Model Based on Revealed and Stated Vehicle Type Choice and Utilisation Data," University of California Transportation Center, Working Papers qt2bz335vw, University of California Transportation Center.
    8. Jonathan Cohen & Keith Marzilli Ericson & David Laibson & John Myles White, 2020. "Measuring Time Preferences," Journal of Economic Literature, American Economic Association, vol. 58(2), pages 299-347, June.
    9. Yves Bentz & Dwight Merunka, 2000. "Neural networks and the multinomial logit for brand choice modelling: a hybrid approach," Post-Print hal-01822273, HAL.
    10. Train,Kenneth E., 2009. "Discrete Choice Methods with Simulation," Cambridge Books, Cambridge University Press, number 9780521747387, October.
    11. Hausman, J. A. & Abrevaya, Jason & Scott-Morton, F. M., 1998. "Misclassification of the dependent variable in a discrete-response setting," Journal of Econometrics, Elsevier, vol. 87(2), pages 239-269, September.
    12. Kenneth Train, 1980. "A Structured Logit Model of Auto Ownership and Mode Choice," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 47(2), pages 357-370.
    13. Golob, Thomas F. & McNally, Michael G., 1997. "A model of activity participation and travel interactions between household heads," Transportation Research Part B: Methodological, Elsevier, vol. 31(3), pages 177-194, June.
    14. Mozolin, M. & Thill, J. -C. & Lynn Usery, E., 2000. "Trip distribution forecasting with multilayer perceptron neural networks: A critical evaluation," Transportation Research Part B: Methodological, Elsevier, vol. 34(1), pages 53-73, January.
    15. Stephane Hess & John Rose, 2009. "Should Reference Alternatives in Pivot Design SC Surveys be Treated Differently?," Environmental & Resource Economics, Springer;European Association of Environmental and Resource Economists, vol. 42(3), pages 297-317, March.
    16. Helveston, John Paul & Feit, Elea McDonnell & Michalek, Jeremy J., 2018. "Pooling stated and revealed preference data in the presence of RP endogeneity," Transportation Research Part B: Methodological, Elsevier, vol. 109(C), pages 70-89.
    17. Train, Kenneth & Wilson, Wesley W., 2008. "Estimation on stated-preference experiments constructed from revealed-preference choices," Transportation Research Part B: Methodological, Elsevier, vol. 42(3), pages 191-203, March.
    18. Small, K. & Winston, C., 1998. ""The Demand for Transportation: Models and Applications"," Papers 98-99-6, California Irvine - School of Social Sciences.
    19. Ye, Xin & Pendyala, Ram M. & Gottardi, Giovanni, 2007. "An exploration of the relationship between mode choice and complexity of trip chaining patterns," Transportation Research Part B: Methodological, Elsevier, vol. 41(1), pages 96-113, January.
    20. Ming Yuan & Yi Lin, 2006. "Model selection and estimation in regression with grouped variables," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 68(1), pages 49-67, February.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Smeele, Nicholas V.R. & Chorus, Caspar G. & Schermer, Maartje H.N. & de Bekker-Grob, Esther W., 2023. "Towards machine learning for moral choice analysis in health economics: A literature review and research agenda," Social Science & Medicine, Elsevier, vol. 326(C).
    2. Shenhao Wang & Baichuan Mo & Jinhua Zhao, 2020. "Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks," Papers 2010.11644, arXiv.org.
    3. Wang, Shenhao & Mo, Baichuan & Zhao, Jinhua, 2021. "Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks," Transportation Research Part B: Methodological, Elsevier, vol. 146(C), pages 333-358.
    4. Wang, Shenhao & Wang, Qingyi & Bailey, Nate & Zhao, Jinhua, 2021. "Deep neural networks for choice analysis: A statistical learning theory perspective," Transportation Research Part B: Methodological, Elsevier, vol. 148(C), pages 60-81.
    5. Liu, Yicong & Loa, Patrick & Wang, Kaili & Habib, Khandker Nurul, 2023. "Theory-driven or data-driven? Modelling ride-sourcing mode choices using integrated choice and latent variable model and multi-task learning deep neural networks," Journal of choice modelling, Elsevier, vol. 48(C).
    6. Ali, Azam & Kalatian, Arash & Choudhury, Charisma F., 2023. "Comparing and contrasting choice model and machine learning techniques in the context of vehicle ownership decisions," Transportation Research Part A: Policy and Practice, Elsevier, vol. 173(C).
    7. Han, Yafei & Pereira, Francisco Camara & Ben-Akiva, Moshe & Zegras, Christopher, 2022. "A neural-embedded discrete choice model: Learning taste representation with strengthened interpretability," Transportation Research Part B: Methodological, Elsevier, vol. 163(C), pages 166-186.
    8. Shenhao Wang & Baichuan Mo & Stephane Hess & Jinhua Zhao, 2021. "Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark," Papers 2102.01130, arXiv.org.
    9. Sfeir, Georges & Abou-Zeid, Maya & Rodrigues, Filipe & Pereira, Francisco Camara & Kaysi, Isam, 2021. "Latent class choice model with a flexible class membership component: A mixture model approach," Journal of choice modelling, Elsevier, vol. 41(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Shenhao Wang & Qingyi Wang & Jinhua Zhao, 2019. "Multitask Learning Deep Neural Networks to Combine Revealed and Stated Preference Data," Papers 1901.00227, arXiv.org, revised Aug 2019.
    2. Wang, Shenhao & Wang, Qingyi & Bailey, Nate & Zhao, Jinhua, 2021. "Deep neural networks for choice analysis: A statistical learning theory perspective," Transportation Research Part B: Methodological, Elsevier, vol. 148(C), pages 60-81.
    3. Shenhao Wang & Qingyi Wang & Nate Bailey & Jinhua Zhao, 2018. "Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective," Papers 1810.10465, arXiv.org, revised Sep 2019.
    4. Shenhao Wang & Baichuan Mo & Jinhua Zhao, 2020. "Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks," Papers 2010.11644, arXiv.org.
    5. Wang, Shenhao & Mo, Baichuan & Zhao, Jinhua, 2021. "Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks," Transportation Research Part B: Methodological, Elsevier, vol. 146(C), pages 333-358.
    6. Rafiq, Rezwana & McNally, Michael G., 2022. "A structural analysis of the work tour behavior of transit commuters," Transportation Research Part A: Policy and Practice, Elsevier, vol. 160(C), pages 61-79.
    7. Daina, Nicolò & Sivakumar, Aruna & Polak, John W., 2017. "Modelling electric vehicles use: a survey on the methods," Renewable and Sustainable Energy Reviews, Elsevier, vol. 68(P1), pages 447-460.
    8. Akar, Gulsah & Clifton, Kelly J. & Doherty, Sean T., 2012. "Redefining activity types: Who participates in which leisure activity?," Transportation Research Part A: Policy and Practice, Elsevier, vol. 46(8), pages 1194-1204.
    9. Xuemei Fu & Zhicai Juan, 2016. "Empirical analysis and comparisons about time-allocation patterns across segments based on mode-specific preferences," Transportation, Springer, vol. 43(1), pages 37-51, January.
    10. Haghani, Milad & Bliemer, Michiel C.J. & Rose, John M. & Oppewal, Harmen & Lancsar, Emily, 2021. "Hypothetical bias in stated choice experiments: Part II. Conceptualisation of external validity, sources and explanations of bias and effectiveness of mitigation methods," Journal of choice modelling, Elsevier, vol. 41(C).
    11. Steven Farber & Antonio Páez & Ruben Mercado & Matthew Roorda & Catherine Morency, 2011. "A time-use investigation of shopping participation in three Canadian cities: is there evidence of social exclusion?," Transportation, Springer, vol. 38(1), pages 17-44, January.
    12. Lin, Zhongjian & Hu, Yingyao, 2024. "Binary choice with misclassification and social interactions, with an application to peer effects in attitude," Journal of Econometrics, Elsevier, vol. 238(1).
    13. Jonas De Vos & Long Cheng & Frank Witlox, 2021. "Do changes in the residential location lead to changes in travel attitudes? A structural equation modeling approach," Transportation, Springer, vol. 48(4), pages 2011-2034, August.
    14. Iragaël Joly & Karl Littlejohn & Vincent Kaufmann, 2006. "La croissance des budgets-temps de transport en question : nouvelles approches," Post-Print halshs-00174992, HAL.
    15. Sandler, Austin M. & Rashford, Benjamin S., 2018. "Misclassification error in satellite imagery data: Implications for empirical land-use models," Land Use Policy, Elsevier, vol. 75(C), pages 530-537.
    16. Jorge González Chapela, 2022. "Is there a patience premium on migration?," Empirical Economics, Springer, vol. 63(4), pages 2025-2055, October.
    17. Metin Senbil & Ryuichi Kitamura & Jamilah Mohamad, 2009. "Residential location, vehicle ownership and travel in Asia: a comparative analysis of Kei-Han-Shin and Kuala Lumpur metropolitan areas," Transportation, Springer, vol. 36(3), pages 325-350, May.
    18. Yingyao Hu & Zhongjian Lin, 2018. "Misclassification and the hidden silent rivalry," CeMMAP working papers CWP12/18, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    19. Loría, Luis Enrique & Watson, Verity & Kiso, Takahiko & Phimister, Euan, 2019. "Investigating users' preferences for Low Emission Buses: Experiences from Europe's largest hydrogen bus fleet," Journal of choice modelling, Elsevier, vol. 32(C), pages 1-1.
    20. Aller, Carlos & González Chapela, Jorge, 2013. "Misclassification of the dependent variable in a debt–repayment behavior context," Journal of Empirical Finance, Elsevier, vol. 23(C), pages 162-172.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:eejocm:v:37:y:2020:i:c:s1755534520300348. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/journal-of-choice-modelling .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.