IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2503.09786.html
   My bibliography  Save this paper

Designing Graph Convolutional Neural Networks for Discrete Choice with Network Effects

Author

Listed:
  • Daniel F. Villarraga
  • Ricardo A. Daziano

Abstract

We introduce a novel model architecture that incorporates network effects into discrete choice problems, achieving higher predictive performance than standard discrete choice models while offering greater interpretability than general-purpose flexible model classes. Econometric discrete choice models aid in studying individual decision-making, where agents select the option with the highest reward from a discrete set of alternatives. Intuitively, the utility an individual derives from a particular choice depends on their personal preferences and characteristics, the attributes of the alternative, and the value their peers assign to that alternative or their previous choices. However, most applications ignore peer influence, and models that do consider peer or network effects often lack the flexibility and predictive performance of recently developed approaches to discrete choice, such as deep learning. We propose a novel graph convolutional neural network architecture to model network effects in discrete choices, achieving higher predictive performance than standard discrete choice models while retaining the interpretability necessary for inference--a quality often lacking in general-purpose deep learning architectures. We evaluate our architecture using revealed commuting choice data, extended with travel times and trip costs for each travel mode for work-related trips in New York City, as well as 2016 U.S. election data aggregated by county, to test its performance on datasets with highly imbalanced classes. Given the interpretability of our models, we can estimate relevant economic metrics, such as the value of travel time savings in New York City. Finally, we compare the predictive performance and behavioral insights from our architecture to those derived from traditional discrete choice and general-purpose deep learning models.

Suggested Citation

  • Daniel F. Villarraga & Ricardo A. Daziano, 2025. "Designing Graph Convolutional Neural Networks for Discrete Choice with Network Effects," Papers 2503.09786, arXiv.org.
  • Handle: RePEc:arx:papers:2503.09786
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2503.09786
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Chandra Bhat, 2015. "A new spatial (social) interaction discrete choice model accommodating for unobserved effects due to endogenous network formation," Transportation, Springer, vol. 42(5), pages 879-914, September.
    2. Train,Kenneth E., 2009. "Discrete Choice Methods with Simulation," Cambridge Books, Cambridge University Press, number 9780521766555, July.
    3. Tomlinson, Kiran & Benson, Austin R., 2024. "Graph-based methods for discrete choice," Network Science, Cambridge University Press, vol. 12(1), pages 21-40, March.
    4. Brock,W.A. & Durlauf,S.N., 2003. "Multinomial choice with social interactions," Working papers 1, Wisconsin Madison - Social Systems.
    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. Frank Goetzke, 2008. "Network Effects in Public Transit Use: Evidence from a Spatially Autoregressive Mode Choice Model for New York," Urban Studies, Urban Studies Journal Limited, vol. 45(2), pages 407-417, February.
    Full references (including those not matched with items on IDEAS)

    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. Di Ciommo, Floridea & Comendador, Julio & López-Lambas, María Eugenia & Cherchi, Elisabetta & Ortúzar, Juan de Dios, 2014. "Exploring the role of social capital influence variables on travel behaviour," Transportation Research Part A: Policy and Practice, Elsevier, vol. 68(C), pages 46-55.
    2. Giulio Zanella, 2004. "Discrete Choice with Social Interactions and Endogenous Memberships," Department of Economics University of Siena 442, Department of Economics, University of Siena.
    3. 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).
    4. Haldun Evrenk & Chien-Yuan Sher, 2015. "Social interactions in voting behavior: distinguishing between strategic voting and the bandwagon effect," Public Choice, Springer, vol. 162(3), pages 405-423, March.
    5. Hu, Wuyang & Adamowicz, Wiktor L. & Veeman, Michele M., 2005. "Bayesian Analysis of Consumer Choices with Taste, Context, Reference Point and Individual Scale Effects," 2005 Annual meeting, July 24-27, Providence, RI 19296, American Agricultural Economics Association (New Name 2008: Agricultural and Applied Economics Association).
    6. Pike, Susan & Lubell, Mark, 2018. "The conditional effects of social influence in transportation mode choice," Research in Transportation Economics, Elsevier, vol. 68(C), pages 2-10.
    7. Oyama, Yuki & Murakami, Daisuke & Krueger, Rico, 2024. "A hierarchical Bayesian logit model for spatial multivariate choice data," Journal of choice modelling, Elsevier, vol. 52(C).
    8. Niousha Bagheri & Milad Ghasri & Michael Barlow, 2025. "RUM-NN: A Neural Network Model Compatible with Random Utility Maximisation for Discrete Choice Setups," Papers 2501.05221, arXiv.org.
    9. Xuli Wen & Xin Chen, 2025. "A New Breakthrough in Travel Behavior Modeling Using Deep Learning: A High-Accuracy Prediction Method Based on a CNN," Sustainability, MDPI, vol. 17(2), pages 1-14, January.
    10. Kim, Eui-Jin & Bansal, Prateek, 2024. "A new flexible and partially monotonic discrete choice model," Transportation Research Part B: Methodological, Elsevier, vol. 183(C).
    11. Zhifeng Gao & Ted C. Schroeder, 2009. "Consumer responses to new food quality information: are some consumers more sensitive than others?," Agricultural Economics, International Association of Agricultural Economists, vol. 40(3), pages 339-346, May.
    12. Cheng, Leilei & Yin, Changbin & Chien, Hsiaoping, 2015. "Demand for milk quantity and safety in urban China: evidence from Beijing and Harbin," Australian Journal of Agricultural and Resource Economics, Australian Agricultural and Resource Economics Society, vol. 59(2), April.
    13. Wen, Chieh-Hua & Huang, Chia-Jung & Fu, Chiang, 2020. "Incorporating continuous representation of preferences for flight departure times into stated itinerary choice modeling," Transport Policy, Elsevier, vol. 98(C), pages 10-20.
    14. Johannes Buggle & Thierry Mayer & Seyhun Orcan Sakalli & Mathias Thoenig, 2023. "The Refugee’s Dilemma: Evidence from Jewish Migration out of Nazi Germany," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 138(2), pages 1273-1345.
    15. Christelis, Dimitris & Dobrescu, Loretti I. & Motta, Alberto, 2020. "Early life conditions and financial risk-taking in older age," The Journal of the Economics of Ageing, Elsevier, vol. 17(C).
    16. Ortega, David L. & Wang, H. Holly & Wu, Laping & Hong, Soo Jeong, 2015. "Retail channel and consumer demand for food quality in China," China Economic Review, Elsevier, vol. 36(C), pages 359-366.
    17. Tina Birgitte Hansen & Jes Sanddal Lindholt & Axel Diederichsen & Rikke Søgaard, 2019. "Do Non-participants at Screening have a Different Threshold for an Acceptable Benefit–Harm Ratio than Participants? Results of a Discrete Choice Experiment," The Patient: Patient-Centered Outcomes Research, Springer;International Academy of Health Preference Research, vol. 12(5), pages 491-501, October.
    18. Doyle, Orla & Fidrmuc, Jan, 2006. "Who favors enlargement?: Determinants of support for EU membership in the candidate countries' referenda," European Journal of Political Economy, Elsevier, vol. 22(2), pages 520-543, June.
    19. Tovar, Jorge, 2012. "Consumers’ Welfare and Trade Liberalization: Evidence from the Car Industry in Colombia," World Development, Elsevier, vol. 40(4), pages 808-820.
    20. Pereira, Pedro & Ribeiro, Tiago, 2011. "The impact on broadband access to the Internet of the dual ownership of telephone and cable networks," International Journal of Industrial Organization, Elsevier, vol. 29(2), pages 283-293, March.

    More about this item

    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:2503.09786. 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.