IDEAS home Printed from https://ideas.repec.org/p/arx/papers/1909.07481.html
   My bibliography  Save this paper

Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions

Author

Listed:
  • Shenhao Wang
  • Baichuan Mo
  • Jinhua Zhao

Abstract

Whereas deep neural network (DNN) is increasingly applied to choice analysis, it is challenging to reconcile domain-specific behavioral knowledge with generic-purpose DNN, to improve DNN's interpretability and predictive power, and to identify effective regularization methods for specific tasks. This study designs a particular DNN architecture with alternative-specific utility functions (ASU-DNN) by using prior behavioral knowledge. Unlike a fully connected DNN (F-DNN), which computes the utility value of an alternative k by using the attributes of all the alternatives, ASU-DNN computes it by using only k's own attributes. Theoretically, ASU-DNN can dramatically reduce the estimation error of F-DNN because of its lighter architecture and sparser connectivity. Empirically, ASU-DNN has 2-3% higher prediction accuracy than F-DNN over the whole hyperparameter space in a private dataset that we collected in Singapore and a public dataset in R mlogit package. The alternative-specific connectivity constraint, as a domain-knowledge-based regularization method, is more effective than the most popular generic-purpose explicit and implicit regularization methods and architectural hyperparameters. ASU-DNN is also more interpretable because it provides a more regular substitution pattern of travel mode choices than F-DNN does. The comparison between ASU-DNN and F-DNN can also aid in testing the behavioral knowledge. Our results reveal that individuals are more likely to compute utility by using an alternative's own attributes, supporting the long-standing practice in choice modeling. Overall, this study demonstrates that prior behavioral knowledge could be used to guide the architecture design of DNN, to function as an effective domain-knowledge-based regularization method, and to improve both the interpretability and predictive power of DNN in choice analysis.

Suggested Citation

  • Shenhao Wang & Baichuan Mo & Jinhua Zhao, 2019. "Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions," Papers 1909.07481, arXiv.org, revised Apr 2021.
  • Handle: RePEc:arx:papers:1909.07481
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/1909.07481
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Peter M. Guadagni & John D. C. Little, 1983. "A Logit Model of Brand Choice Calibrated on Scanner Data," Marketing Science, INFORMS, vol. 2(3), pages 203-238.
    2. Train,Kenneth E., 2009. "Discrete Choice Methods with Simulation," Cambridge Books, Cambridge University Press, number 9780521766555, September.
    3. Dhami, Sanjit, 2016. "The Foundations of Behavioral Economic Analysis," OUP Catalogue, Oxford University Press, number 9780198715535.
    4. Yves Bentz & Dwight Merunka, 2000. "Neural networks and the multinomial logit for brand choice modelling: a hybrid approach," Post-Print hal-01822273, HAL.
    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. 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.
    2. 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.
    3. Andrés Elberg & Pedro M. Gardete & Rosario Macera & Carlos Noton, 2019. "Dynamic effects of price promotions: field evidence, consumer search, and supply-side implications," Quantitative Marketing and Economics (QME), Springer, vol. 17(1), pages 1-58, March.
    4. Gelhausen, Marc Christopher, 2007. "A Generalized Neural Logit Model for Airport and Access Mode Choice in Germany," MPRA Paper 4313, University Library of Munich, Germany, revised 2007.
    5. Aydın Alptekinoğlu & John H. Semple, 2016. "The Exponomial Choice Model: A New Alternative for Assortment and Price Optimization," Operations Research, INFORMS, vol. 64(1), pages 79-93, February.
    6. Guyt, Jonne & Gijsbrechts, Els, 2018. "On consumer choice patterns and the net impact of feature promotions," International Journal of Research in Marketing, Elsevier, vol. 35(3), pages 490-508.
    7. Andrew T. Ching & Tülin Erdem & Michael P. Keane, 2020. "How much do consumers know about the quality of products? Evidence from the diaper market," The Japanese Economic Review, Springer, vol. 71(4), pages 541-569, October.
    8. Granlund, David & Sundström, David, 2018. "Physicians prescribing originals causes welfare losses," Economics Letters, Elsevier, vol. 170(C), pages 143-146.
    9. Juan Luis Nicolau, 2006. "Does The Consumer'S Variety-Seeking Behavior Condition The Willingness To Travel Further?," Working Papers. Serie EC 2006-17, Instituto Valenciano de Investigaciones Económicas, S.A. (Ivie).
    10. Youssef M. Aboutaleb & Mazen Danaf & Yifei Xie & Moshe Ben-Akiva, 2021. "Discrete Choice Analysis with Machine Learning Capabilities," Papers 2101.10261, arXiv.org.
    11. 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.
    12. 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).
    13. Yina Lu & Andrés Musalem & Marcelo Olivares & Ariel Schilkrut, 2013. "Measuring the Effect of Queues on Customer Purchases," Management Science, INFORMS, vol. 59(8), pages 1743-1763, August.
    14. Shivaram Subramanian & Pavithra Harsha, 2021. "Demand Modeling in the Presence of Unobserved Lost Sales," Management Science, INFORMS, vol. 67(6), pages 3803-3833, June.
    15. Lee, Yinjin & Bateman, Alexis, 2021. "The competitiveness of fair trade and organic versus conventional coffee based on consumer panel data," Ecological Economics, Elsevier, vol. 184(C).
    16. Bruno Jacobs & Dennis Fok & Bas Donkers, 2021. "Understanding Large-Scale Dynamic Purchase Behavior," Marketing Science, INFORMS, vol. 40(5), pages 844-870, September.
    17. Allender, William J. & Richards, Timothy J., 2012. "Brand Loyalty and Price Promotion Strategies: An Empirical Analysis," Journal of Retailing, Elsevier, vol. 88(3), pages 323-342.
    18. Haghani, Milad & Bliemer, Michiel C.J. & Hensher, David A., 2021. "The landscape of econometric discrete choice modelling research," Journal of choice modelling, Elsevier, vol. 40(C).
    19. Zhang, Jian & Nault, Barrie R. & Tu, Yiliu, 2015. "A dynamic pricing strategy for a 3PL provider with heterogeneous customers," International Journal of Production Economics, Elsevier, vol. 169(C), pages 31-43.
    20. Elshiewy, Ossama & Peschel, Anne O., 2022. "Internal reference price response across store formats," Journal of Retailing, Elsevier, vol. 98(3), pages 496-509.

    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:1909.07481. 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.