Skip to main content

Part of the book series: Springer Series in Supply Chain Management ((SSSCM,volume 18))

  • 777 Accesses

Abstract

Choice-based demand models serve as building blocks for making demand predictions, which are key inputs to critical operational decisions, such as what prices to charge for different products or which subset of products to offer to the customers. Traditionally, parametric choice models (such as the multinomial logit model) have been employed for tractability reasons, but with the increasing ability of firms to collect large volumes of sales transaction and product availability data, nonparametric choice models have been gaining in popularity. We review recent advances in nonparametric estimation of two versatile choice model families.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    However, they did not introduce this nomenclature.

  2. 2.

    There are numerous papers that explicitly account for the demand censoring issue while estimating the choice model; see, for instance, Haensel and Koole (2011), Newman et al. (2014), and Abdallah and Vulcano (2020).

  3. 3.

    This is true as long as \(\left <\nabla h (\boldsymbol {x}^{(k-1)}), \boldsymbol {v}^{(k)} - \boldsymbol {x}^{(k-1)}\right > < 0\). If \(\left <\nabla h (\boldsymbol {x}^{(k-1)}), \boldsymbol {v}^{(k)} - \boldsymbol {x}^{(k-1)}\right > \geq 0\), then the convexity of h(⋅) implies that h(x) ≥ h(x(k−1)) for all \(\boldsymbol {x} \in \mathcal {D}\) and consequently, x(k−1) is an optimal solution.

  4. 4.

    We abuse notation and denote αf(σ) as ασ for any \(\sigma \in \mathcal {P}\) in the remainder of this section.

  5. 5.

    Mišić (2016) also proposed a similar formulation for estimating the rank-based choice model with an L1-norm loss function using a column generation approach.

  6. 6.

    The remaining products in each ranking can be chosen arbitrarily.

  7. 7.

    In this case, the feature vector for other products would typically include a constant feature 1 to allow for general no-purchase market shares.

  8. 8.

    Our development here is closely related to that in JSV but with slight differences.

  9. 9.

    Technically, the distribution is modeled over the parameter vector β as opposed to its “type” representation f(β).

  10. 10.

    This is equivalent to minimizing the KL-divergence loss function and is the standard choice when estimating the mixed logit model.

  11. 11.

    The rank-based model can allow for the number of products in a ranking to be strictly smaller than the size of the product universe, in which case the customer selects the no-purchase option if none of the products in the ranking is part of the offer set.

References

  • Abdallah, T., & Vulcano, G. (2020). Demand estimation under the multinomial logit model from sales transaction data. Manufacturing & Service Operations Management, 23, 1005–1331.

    Google Scholar 

  • Aouad, A., Elmachtoub, A. N., Ferreira, K. J., & McNellis, R. (2020a). Market segmentation trees. arXiv:1906.01174.

    Google Scholar 

  • Aouad, A., Farias, V., & Levi, R. (2020b). Assortment optimization under consider-then-choose choice models. Management Science, 67, 3321–3984.

    Google Scholar 

  • Barberá, S., & Pattanaik, P. K. (1986). Falmagne and the rationalizability of stochastic choices in terms of random orderings. Econometrica: Journal of the Econometric Society, 54, 707–715.

    Google Scholar 

  • Ben-Akiva, M. E., Lerman, S. R., & Lerman, S. R. (1985). Discrete choice analysis: Theory and application to travel demand (vol. 9). Cambridge: MIT Press.

    Google Scholar 

  • Berbeglia, G. (2018). The generalized stochastic preference choice model. Available at SSRN 3136227.

    Google Scholar 

  • Bertsimas, D., & Mišić, V. V. (2019). Exact first-choice product line optimization. Operations Research, 67(3), 651–670.

    Google Scholar 

  • Bhat, C. R. (1997). An endogenous segmentation mode choice model with an application to intercity travel. Transportation Science, 31(1), 34–48.

    Google Scholar 

  • Block, H. D., & Marschak, J. (1960). Random orderings and stochastic theories of responses. Contributions to Probability and Statistics, 2, 97–132.

    Google Scholar 

  • Boxall, P. C., & Adamowicz, W. L. (2002). Understanding heterogeneous preferences in random utility models: A latent class approach. Environmental and Resource Economics, 23(4), 421–446.

    Google Scholar 

  • Chen, N., Gallego, G., & Tang, Z. (2019). The use of binary choice forests to model and estimate discrete choices. Available at SSRN 3430886.

    Google Scholar 

  • Chen, Y. C., & Mišić, V. (2019). Decision forest: A nonparametric approach to modeling irrational choice. Available at SSRN 3376273.

    Google Scholar 

  • Clarkson, K. L. (2010). Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm. ACM Transactions on Algorithms, 6(4), 63.

    Google Scholar 

  • Désir, A., Goyal, V., Jagabathula, S., & Segev, D. (2021). Mallows-smoothed distribution over rankings approach for modeling choice. Operations Research, 69, 1015–1348.

    Google Scholar 

  • Dwork, C., Kumar, R., Naor, M., & Sivakumar, D. (2001). Rank aggregation methods for the web. In Proceedings of the 10th International Conference on World Wide Web (pp. 613–622). New York: ACM.

    Google Scholar 

  • Falmagne, J. C. (1978). A representation theorem for finite random scale systems. Journal of Mathematical Psychology, 18(1), 52–72.

    Google Scholar 

  • Farias, V. F., Jagabathula, S., & Shah, D. (2013). A nonparametric approach to modeling choice with limited data. Management Science, 59(2), 305–322.

    Google Scholar 

  • Fox, J. T., il Kim, K., Ryan, S. P., & Bajari, P. (2011). A simple estimator for the distribution of random coefficients. Quantitative Economics, 2(3), 381–418.

    Google Scholar 

  • Frank, M., & Wolfe, P. (1956). An algorithm for quadratic programming. Naval Research Logistics Quarterly, 3(1–2), 95–110.

    Google Scholar 

  • Gallego, G., Ratliff, R., & Shebalov, S. (2015). A general attraction model and sales-based linear program for network revenue management under customer choice. Operations Research, 63(1), 212–232.

    Google Scholar 

  • Gallego, G., & Topaloglu, H. (2019). Introduction to choice modeling. In Revenue management and pricing analytics (pp. 109–128). Berlin: Springer.

    Google Scholar 

  • Greene, W. H., & Hensher, D. A. (2003). A latent class model for discrete choice analysis: Contrasts with mixed logit. Transportation Research Part B: Methodological, 37(8), 681–698.

    Google Scholar 

  • Guélat, J., & Marcotte, P. (1986). Some comments on wolfe’s ‘away step’. Mathematical Programming, 35(1), 110–119.

    Google Scholar 

  • Haensel, A., & Koole, G. (2011). Estimating unconstrained demand rate functions using customer choice sets. Journal of Revenue and Pricing Management, 10(5), 438–454.

    Google Scholar 

  • Han, Y., Zegras, C., Pereira, F. C., & Ben-Akiva, M. (2020). A neural-embedded choice model: Tastenet-mnl modeling taste heterogeneity with flexibility and interpretability. arXiv:200200922.

    Google Scholar 

  • Hauser, J. R. (2014). Consideration-set heuristics. Journal of Business Research, 67(8), 1688–1699.

    Google Scholar 

  • Hensher, D. A., & Greene, W. H. (2003). The mixed logit model: The state of practice. Transportation, 30(2), 133–176.

    Google Scholar 

  • Honhon, D., Jonnalagedda, S., & Pan, X. A. (2012). Optimal algorithms for assortment selection under ranking-based consumer choice models. Manufacturing & Service Operations Management, 14(2), 279–289.

    Google Scholar 

  • Hoyer, W. D., & Ridgway, N. M. (1984). Variety seeking as an explanation for exploratory purchase behavior: A theoretical model. In T. C. Kinnear (Ed.), NA - Advances in consumer research (vol. 11, pp. 114–119). Provo: ACR North American Advances.

    Google Scholar 

  • Hunter, D. R. (2004). MM algorithms for generalized bradley-terry models. Annals of Statistics, 32, 384–406.

    Google Scholar 

  • Jagabathula, S., & Rusmevichientong, P. (2017). A nonparametric joint assortment and price choice model. Management Science, 63(9), 3128–3145.

    Google Scholar 

  • Jagabathula, S., Mitrofanov, D., & Vulcano, G. (2020a). Personalized retail promotions through a dag-based representation of customer preferences. Operations Research, 70, 641–1291.

    Google Scholar 

  • Jagabathula, S., & Rusmevichientong, P. (2019). The limit of rationality in choice modeling: Formulation, computation, and implications. Management Science, 65(5), 2196–2215.

    Google Scholar 

  • Jagabathula, S., Subramanian, L., & Venkataraman, A. (2020b). A conditional gradient approach for nonparametric estimation of mixing distributions. Management Science, 66(8), 3635–3656.

    Google Scholar 

  • Jagabathula, S., & Venkataraman, A. (2020). An MM algorithm for estimating the MNL model with product features. Available at SSRN: https://ssrncom/abstract=3733971

  • Jagabathula, S., & Vulcano, G. (2018). A partial-order-based model to estimate individual preferences using panel data. Management Science, 64(4), 1609–1628.

    Google Scholar 

  • Jaggi, M. (2011). Sparse convex optimization methods for machine learning. Ph.D. Thesis, ETH Zürich.

    Google Scholar 

  • Jaggi, M. (2013). Revisiting frank-wolfe: Projection-free sparse convex optimization. In Proceedings of the 30th International Conference on Machine Learning (ICML-13) (pp. 427–435).

    Google Scholar 

  • Kahn, B. E., & Lehmann, D. R. (1991). Modeling choice among assortments. Journal of Retailing, 67(3), 274–300.

    Google Scholar 

  • Krishnan, R. G., Lacoste-Julien, S., & Sontag, D. (2015). Barrier frank-wolfe for marginal inference. In Advances in Neural Information Processing Systems (vol. 28, pp. 532–540)

    Google Scholar 

  • Li, G., Rusmevichientong, P., & Topaloglu, H. (2015). The d-level nested logit model: Assortment and price optimization problems. Operations Research, 63(2), 325–342.

    Google Scholar 

  • Lindsay, B. G. (1983). The geometry of mixture likelihoods: A general theory. The Annals of Statistics, 11, 86–94.

    Google Scholar 

  • Liu, L., Dzyabura, D., & Mizik, N. (2020). Visual listening in: Extracting brand image portrayed on social media. Marketing Science, 39(4), 669–686.

    Google Scholar 

  • Liu, X., Lee, D., & Srinivasan, K. (2019). Large-scale cross-category analysis of consumer review content on sales conversion leveraging deep learning. Journal of Marketing Research, 56(6), 918–943.

    Google Scholar 

  • Luce, R. D. (1959). Individual Choice Behavior: A Theoretical analysis. New York: Wiley.

    Google Scholar 

  • Mahajan, S., & Van Ryzin, G. (2001). Stocking retail assortments under dynamic consumer substitution. Operations Research, 49(3), 334–351.

    Google Scholar 

  • Mallows, C. L. (1957). Non-null ranking models. I. Biometrika, 44(1–2), 114–130.

    Google Scholar 

  • Manski, C. F. (1977). The structure of random utility models. Theory and Decision, 8(3), 229–254.

    Google Scholar 

  • Mas-Colell, A., Whinston, M. D., Green. J. R. (1995). Microeconomic theory (vol 1). New York: Oxford University Press.

    Google Scholar 

  • McFadden, D. (1981). Econometric models of probabilistic choice. In: Structural analysis of discrete data with econometric applications (pp. 198–272). Cambridge: MIT Press.

    Google Scholar 

  • McFadden, D., & Train, K. (2000). Mixed MNL models for discrete response. Journal of Applied Econometrics, 15, 447–470.

    Google Scholar 

  • McFadden, D. L. (2005). Revealed stochastic preference: A synthesis. Economic Theory, 26(2), 245–264.

    Google Scholar 

  • McLachlan, G., & Peel, D. (2004). Finite mixture models. Hoboken: Wiley.

    Google Scholar 

  • Mišić, V. V. (2016). Data, models and decisions for large-scale stochastic optimization problems. Ph. D. Thesis, Massachusetts Institute of Technology, chapter 4: Data-driven Assortment Optimization.

    Google Scholar 

  • Newman, J. P., Ferguson, M. E., Garrow, L. A., & Jacobs, T. L. (2014). Estimation of choice-based models using sales data from a single firm. Manufacturing & Service Operations Management, 16(2), 184–197.

    Google Scholar 

  • Nocedal, J., & Wright, S. J. (2006). Numerical optimization (2nd edn.). Berlin: Springer.

    Google Scholar 

  • Paul, A., Feldman, J., & Davis, J. M. (2018). Assortment optimization and pricing under a nonparametric tree choice model. Manufacturing & Service Operations Management, 20(3), 550–565.

    Google Scholar 

  • Prechelt, L. (2012). Early stopping—but when? In Neural networks: Tricks of the trade (pp. 53–67), Berlin: Springer.

    Google Scholar 

  • Rusmevichientong, P., Shmoys, D., Tong, C., & Topaloglu, H. (2014). Assortment optimization under the multinomial logit model with random choice parameters. Production and Operations Management, 23(11), 2023–2039.

    Google Scholar 

  • Shalev-Shwartz, S., Srebro, N., & Zhang, T. (2010). Trading accuracy for sparsity in optimization problems with sparsity constraints. SIAM Journal on Optimization, 20(6), 2807–2832.

    Google Scholar 

  • Sher, I., Fox, J. T., il Kim, K., & Bajari, P. (2011). Partial identification of heterogeneity in preference orderings over discrete choices. Tech. Rep., National Bureau of Economic Research.

    Google Scholar 

  • Sifringer, B., Lurkin, V., & Alahi, A. (2020). Enhancing discrete choice models with representation learning. Transportation Research Part B: Methodological, 140, 236–261.

    Google Scholar 

  • Strauss, A. K., Klein, R., & Steinhardt, C. (2018). A review of choice-based revenue management: Theory and methods. European Journal of Operational Research, 271(2), 375–387.

    Google Scholar 

  • Train, K. E. (2008). EM algorithms for nonparametric estimation of mixing distributions. Journal of Choice Modelling, 1(1), 40–69.

    Google Scholar 

  • Train, K. E. (2009). Discrete choice methods with simulation. Cambridge: Cambridge University Press.

    Google Scholar 

  • van Ryzin, G., & Vulcano, G. (2015). A market discovery algorithm to estimate a general class of nonparametric choice models. Management Science, 61(2), 281–300.

    Google Scholar 

  • van Ryzin, G., & Vulcano, G. (2017). An expectation-maximization method to estimate a rank-based choice model of demand. Operations Research, 65(2), 396–407.

    Google Scholar 

  • Yao, Y., Rosasco, L., & Caponnetto, A. (2007). On early stopping in gradient descent learning. Constructive Approximation, 26(2), 289–315.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ashwin Venkataraman .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Jagabathula, S., Venkataraman, A. (2022). Nonparametric Estimation of Choice Models. In: Chen, X., Jasin, S., Shi, C. (eds) The Elements of Joint Learning and Optimization in Operations Management. Springer Series in Supply Chain Management, vol 18. Springer, Cham. https://doi.org/10.1007/978-3-031-01926-5_8

Download citation

Publish with us

Policies and ethics