IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2109.12042.html
   My bibliography  Save this paper

Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance

Author

Listed:
  • Ioanna Arkoudi
  • Carlos Lima Azevedo
  • Francisco C. Pereira

Abstract

This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs). In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables with a special focus on interpretability and model transparency. Although embedding representations within the logit framework have been conceptualized by Pereira (2019), their dimensions do not have an absolute definitive meaning, hence offering limited behavioral insights in this earlier work. The novelty of our work lies in enforcing interpretability to the embedding vectors by formally associating each of their dimensions to a choice alternative. Thus, our approach brings benefits much beyond a simple parsimonious representation improvement over dummy encoding, as it provides behaviorally meaningful outputs that can be used in travel demand analysis and policy decisions. Additionally, in contrast to previously suggested ANN-based Discrete Choice Models (DCMs) that either sacrifice interpretability for performance or are only partially interpretable, our models preserve interpretability of the utility coefficients for all the input variables despite being based on ANN principles. The proposed models were tested on two real world datasets and evaluated against benchmark and baseline models that use dummy-encoding. The results of the experiments indicate that our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.

Suggested Citation

  • Ioanna Arkoudi & Carlos Lima Azevedo & Francisco C. Pereira, 2021. "Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance," Papers 2109.12042, arXiv.org, revised Sep 2021.
  • Handle: RePEc:arx:papers:2109.12042
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2109.12042
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sendhil Mullainathan & Jann Spiess, 2017. "Machine Learning: An Applied Econometric Approach," Journal of Economic Perspectives, American Economic Association, vol. 31(2), pages 87-106, Spring.
    2. Hruschka, Harald & Fettes, Werner & Probst, Markus, 2004. "An empirical comparison of the validity of a neural net based multinomial logit choice model to alternative model specifications," European Journal of Operational Research, Elsevier, vol. 159(1), pages 166-180, November.
    3. Philip Salesses & Katja Schechtner & César A Hidalgo, 2013. "The Collaborative Image of The City: Mapping the Inequality of Urban Perception," PLOS ONE, Public Library of Science, vol. 8(7), pages 1-12, July.
    4. Francisco C. Pereira, 2019. "Rethinking travel behavior modeling representations through embeddings," Papers 1909.00154, arXiv.org.
    5. Ben-Akiva, Moshe & McFadden, Daniel & Train, Kenneth & Börsch-Supan, Axel, 2002. "Hybrid Choice Models: Progress and Challenges," Sonderforschungsbereich 504 Publications 02-29, Sonderforschungsbereich 504, Universität Mannheim;Sonderforschungsbereich 504, University of Mannheim.
    6. Sifringer, Brian & Lurkin, Virginie & Alahi, Alexandre, 2020. "Enhancing discrete choice models with representation learning," Transportation Research Part B: Methodological, Elsevier, vol. 140(C), pages 236-261.
    7. Cherchi, Elisabetta & Guevara, Cristian Angelo, 2012. "A Monte Carlo experiment to analyze the curse of dimensionality in estimating random coefficients models with a full variance–covariance matrix," Transportation Research Part B: Methodological, Elsevier, vol. 46(2), pages 321-332.
    8. Brathwaite, Timothy & Walker, Joan L., 2018. "Asymmetric, closed-form, finite-parameter models of multinomial choice," Journal of choice modelling, Elsevier, vol. 29(C), pages 78-112.
    9. John Rose & Michiel Bliemer, 2013. "Sample size requirements for stated choice experiments," Transportation, Springer, vol. 40(5), pages 1021-1041, September.
    10. Cinzia Cirillo & Renting Xu, 2011. "Dynamic Discrete Choice Models for Transportation," Transport Reviews, Taylor & Francis Journals, vol. 31(4), pages 473-494.
    11. Glerum, Aurélie & Atasoy, Bilge & Bierlaire, Michel, 2014. "Using semi-open questions to integrate perceptions in choice models," Journal of choice modelling, Elsevier, vol. 10(C), pages 11-33.
    12. Yves Bentz & Dwight Merunka, 2000. "Neural networks and the multinomial logit for brand choice modelling: a hybrid approach," Post-Print hal-01822273, HAL.
    13. Yafei Han & Francisco Camara Pereira & Moshe Ben-Akiva & Christopher Zegras, 2020. "A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability," Papers 2002.00922, arXiv.org, revised Jul 2022.
    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. Weitao Jian & Kunxu Chen & Junshu He & Sifan Wu & Hongli Li & Ming Cai, 2023. "A Federated Personal Mobility Service in Autonomous Transportation Systems," Mathematics, MDPI, vol. 11(12), pages 1-21, June.
    3. Lorena Torres Lahoz & Francisco Camara Pereira & Georges Sfeir & Ioanna Arkoudi & Mayara Moraes Monteiro & Carlos Lima Azevedo, 2023. "Attitudes and Latent Class Choice Models using Machine learning," Papers 2302.09871, arXiv.org.
    4. Qingyi Wang & Shenhao Wang & Yunhan Zheng & Hongzhou Lin & Xiaohu Zhang & Jinhua Zhao & Joan Walker, 2023. "Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?," Papers 2303.04204, arXiv.org, revised Feb 2024.
    5. Sander van Cranenburgh & Francisco Garrido-Valenzuela, 2023. "Computer vision-enriched discrete choice models, with an application to residential location choice," Papers 2308.08276, arXiv.org.

    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. Arkoudi, Ioanna & Krueger, Rico & Azevedo, Carlos Lima & Pereira, Francisco C., 2023. "Combining discrete choice models and neural networks through embeddings: Formulation, interpretability and performance," Transportation Research Part B: Methodological, Elsevier, vol. 175(C).
    2. S. Van Cranenburgh & S. Wang & A. Vij & F. Pereira & J. Walker, 2021. "Choice modelling in the age of machine learning -- discussion paper," Papers 2101.11948, arXiv.org, revised Nov 2021.
    3. 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).
    4. Sifringer, Brian & Lurkin, Virginie & Alahi, Alexandre, 2020. "Enhancing discrete choice models with representation learning," Transportation Research Part B: Methodological, Elsevier, vol. 140(C), pages 236-261.
    5. 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.
    6. Lorena Torres Lahoz & Francisco Camara Pereira & Georges Sfeir & Ioanna Arkoudi & Mayara Moraes Monteiro & Carlos Lima Azevedo, 2023. "Attitudes and Latent Class Choice Models using Machine learning," Papers 2302.09871, arXiv.org.
    7. Ortelli, Nicola & Hillel, Tim & Pereira, Francisco C. & de Lapparent, Matthieu & Bierlaire, Michel, 2021. "Assisted specification of discrete choice models," Journal of choice modelling, Elsevier, vol. 39(C).
    8. Galdo, Virgilio & Li, Yue & Rama, Martin, 2021. "Identifying urban areas by combining human judgment and machine learning: An application to India," Journal of Urban Economics, Elsevier, vol. 125(C).
    9. 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).
    10. Yafei Han & Francisco Camara Pereira & Moshe Ben-Akiva & Christopher Zegras, 2020. "A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability," Papers 2002.00922, arXiv.org, revised Jul 2022.
    11. Guevara, C. Angelo, 2015. "Critical assessment of five methods to correct for endogeneity in discrete-choice models," Transportation Research Part A: Policy and Practice, Elsevier, vol. 82(C), pages 240-254.
    12. Harald Hruschka, 2007. "Using a heterogeneous multinomial probit model with a neural net extension to model brand choice," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 26(2), pages 113-127.
    13. Beeramoole, Prithvi Bhat & Arteaga, Cristian & Pinz, Alban & Haque, Md Mazharul & Paz, Alexander, 2023. "Extensive hypothesis testing for estimation of mixed-Logit models," Journal of choice modelling, Elsevier, vol. 47(C).
    14. Mariel, Petr & Meyerhoff, Jürgen & Hess, Stephane, 2015. "Heterogeneous preferences toward landscape externalities of wind turbines – combining choices and attitudes in a hybrid model," Renewable and Sustainable Energy Reviews, Elsevier, vol. 41(C), pages 647-657.
    15. Qingyi Wang & Shenhao Wang & Yunhan Zheng & Hongzhou Lin & Xiaohu Zhang & Jinhua Zhao & Joan Walker, 2023. "Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?," Papers 2303.04204, arXiv.org, revised Feb 2024.
    16. Fernández-Antolín, Anna & Guevara, C. Angelo & de Lapparent, Matthieu & Bierlaire, Michel, 2016. "Correcting for endogeneity due to omitted attitudes: Empirical assessment of a modified MIS method using RP mode choice data," Journal of choice modelling, Elsevier, vol. 20(C), pages 1-15.
    17. 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.
    18. 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.
    19. Teodóra Szép & Sander Cranenburgh & Caspar Chorus, 2024. "Moral rhetoric in discrete choice models: a Natural Language Processing approach," Quality & Quantity: International Journal of Methodology, Springer, vol. 58(1), pages 179-206, February.
    20. La Paix Puello, Lissy & Olde-Kalter, Marie-José & Geurs, Karst T., 2017. "Measurement of non-random attrition effects on mobility rates using trip diaries data," Transportation Research Part A: Policy and Practice, Elsevier, vol. 106(C), pages 51-64.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    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:arx:papers:2109.12042. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.