Skip to main content

Estimating heterogeneous agent preferences by inverse optimization in a randomized nonatomic game

Abstract

We consider an externality game in which nonatomic agents choose from a finite set of alternatives and disutility is determined only by the number of agents choosing each alternative. The equilibrium is defined with respect to the agents’ choices so that taste heterogeneity, modeled through randomized parameters, can be estimated from collective choice data. The joint density of the taste parameters is computed by a biquadratic inverse optimization process that matches observed choices to the equilibrium condition associated with a set-valued best-response function, and hence imposes no prior assumptions on the taste parameters. The model is capacitated with disutility generalized into an arbitrary function that is continuous in attributes and measurable in taste parameters. The existence of an equilibrium under such a disutility model is established by observing that, in an externality game, the proposed aggregate equilibrium is actually equivalent to the agent-specific Nash equilibrium previously established by Schmeidler (J Stat Phys 7(4):295–300, 1973). In a comparison test on intensive metro route-choice data, we demonstrate that the proposed model is a good alternative to existing nongame choice models. An extended test also demonstrates the advantage of the general disutility model in describing agents choice behaviors in other contexts.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. Ahuja, R. K., & Orlin, J. B. (2001). Inverse optimization. Operations Research, 49(5), 771–783.

    Google Scholar 

  2. Allen, R. G. D. (1938). Mathematical analysis for economists. London: Macmillan.

    Google Scholar 

  3. Arrow, K. J., Chenery, H. B., Minhas, B. S., & Solow, R. M. (1961). Capital-labor substitution and economic efficiency. The Review of Economics and Statistics, 43(3), 225–250.

    Google Scholar 

  4. Aumann, R. J. (1965). Integrals of set-valued functions. Journal of Mathematical Analysis and Applications, 12(1), 1–12.

    Google Scholar 

  5. Axhausen, K., Horni, A. & Nagel, K. ( 2016). The multi-agent transport simulation MATSim.

  6. Beckmann, M., McGuire, C. B., & Winsten, C. B. (1956). Studies in the Economics of Transportation. Yale: Yale University Press.

    Google Scholar 

  7. Bertsimas, D., Gupta, V., & Paschalidis, I. C. (2015). Data-driven estimation in equilibrium using inverse optimization. Mathematical Programming, 153(2), 1–39.

    Google Scholar 

  8. Bhat, C. R. (1998). Accommodating variations in responsiveness to level-of-service measures in travel mode choice modeling. Transportation Research Part A: Policy and Practice, 32(7), 495–507.

    Google Scholar 

  9. Blackwell, D. (1951). The range of certain vector integrals. Proceedings of the American Mathematical Society, 2(3), 390–395.

    Google Scholar 

  10. Bomze, I. M., Ling, C., Qi, L., & Zhang, X. (2012). Standard bi-quadratic optimization problems and unconstrained polynomial reformulations. Journal of Global Optimization, 52(4), 663–687.

    Google Scholar 

  11. Brown, G. W. & Von Neumann, J. ( 1950). Solutions of games by differential equations.

  12. Chen, A., Ji, Z., & Recker, W. (2002). Travel time reliability with risk-sensitive travelers. Transportation Research Record: Journal of the Transportation Research Board, 1783, 27–33.

    Google Scholar 

  13. Cheridito, P., Horst, U., Kupper, M., & Pirvu, T. A. (2015). Equilibrium pricing in incomplete markets under translation invariant preferences. Mathematics of Operations Research, 41(1), 174–195.

    Google Scholar 

  14. Dafermos, S. C. (1972). The traffic assignment problem for multiclass-user transportation networks. Transportation Science, 6(1), 73–87.

    Google Scholar 

  15. Dial, R. B. (1996). Bicriterion traffic assignment: Basic theory and elementary algorithms. Transportation Science, 30(2), 93–111.

    Google Scholar 

  16. Epstein, L. G. (1988). Risk aversion and asset prices. Journal of Monetary Economics, 22(2), 179–192.

    Google Scholar 

  17. Fellendorf, M., & Vortisch, P. (2010). Microscopic traffic flow simulator VISSIM, International Series in Operations Research & Management. Science, 145, 63–93.

    Google Scholar 

  18. Fisk, C. (1980). Some developments in equilibrium traffic assignment. Transportation Research Part B: Methodological, 14(3), 243–255.

    Google Scholar 

  19. Fosgerau, M. (2007). Using nonparametrics to specify a model to measure the value of travel time. Transportation Research Part A: Policy and Practice, 41(9), 842–856.

    Google Scholar 

  20. Fox, J. T., 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 

  21. Heckman, J. J. (2001). Micro data, heterogeneity, and the evaluation of public policy: Nobel lecture. Journal of Political Economy, 109(4), 673–748.

    Google Scholar 

  22. Hong, S.-P., Kim, K. M., Byeon, G., & Min, Y.-H. (2017). A method to directly derive taste heterogeneity of travellers route choice in public transport from observed routes. Transportation Research Part B: Methodological, 95, 41–52.

    Google Scholar 

  23. Hong, S.-P., Min, Y.-H., Park, M.-J., Kim, K. M., & Oh, S. M. (2016). Precise estimation of connections of metro passengers from Smart Card data. Transportation, 43(5), 749–769.

    Google Scholar 

  24. Jang, S., Rasouli, S., & Timmermans, H. (2017). Bias in random regret models due to measurement error: Formal and empirical comparison with random utility model. Transportmetrica A: Transport Science, 13(5), 405–434.

    Google Scholar 

  25. Kakutani, S. (1941). A generalization of Brouwer’s fixed point theorem. Duke Mathematical Journal 8, 457–459.

  26. Kim, D. ( 2014). Improvement of path selecting cost function for Seoul metropolitan area using Smart Card data. MS thesis. Seoul National University.

  27. Kim, K. M., Hong, S.-P., Ko, S.-J., & Kim, D. (2015). Does crowding affect the path choice of metro passengers? Transportation Research Part A: Policy and Practice, 77, 292–304.

    Google Scholar 

  28. Klump, R., McAdam, P., & Willman, A. (2007). Factor substitution and factor-augmenting technical progress in the United States: A normalized supply-side system approach. The Review of Economics and Statistics, 89(1), 183–192.

    Google Scholar 

  29. Knowles, J. K., & Sternberg, E. (1975). On the ellipticity of the equations of nonlinear elastostatics for a special material. Journal of Elasticity, 5(3–4), 341–361.

    Google Scholar 

  30. Konishi, H. (2004). Uniqueness of user equilibrium in transportation networks with heterogeneous commuters. Transportation Science, 38(3), 315–330.

    Google Scholar 

  31. Konno, H. ( 1971) , Bilinear programming: Part I. Algorithm for solving bilinear programs, Technical Report 71-9, Operations Research House, Stanford University (Stanford, CA).

  32. Konno, H. (1976). A cutting plane algorithm for solving bilinear programs. Mathematical Programming, 11(1), 14–27.

    Google Scholar 

  33. Korea Railroad Research Institute (2010). Development of NxTIS to implement railway oriented public transportation framework (In Korean), Technical Report 2010-132.

  34. Leurent, F. (1993). Cost versus time equilibrium over a network. European Journal of Operational Research, 71(2), 205–221.

    Google Scholar 

  35. Ling, C., Nie, J., Qi, L., & Ye, Y. (2009). Biquadratic optimization over unit spheres and semidefinite programming relaxations. SIAM Journal on Optimization, 20(3), 1286–1310.

    Google Scholar 

  36. Ling, C., Zhang, X., & Qi, L. (2012). Semidefinite relaxation approximation for multivariate bi-quadratic optimization with quadratic constraints. Numerical Linear Algebra with Applications, 19(1), 113–131.

    Google Scholar 

  37. Mandel, B., Gaudry, M., & Rothengatter, W. (1994). Linear or nonlinear utility functions in logit models? The impact on German high-speed rail demand forecasts. Transportation Research Part B: Methodological, 28(2), 91–101.

    Google Scholar 

  38. Marcotte, P., & Zhu, D. L. (1997). Equilibria with infinitely many differentiated classes of customers. Philadelphia: SIAM.

    Google Scholar 

  39. McFadden, D., & Train, K. E. (2000). Mixed MNL models for discrete response. Journal of Applied Econometrics, 15(5), 447–470.

    Google Scholar 

  40. Meunier, F., & Pradeau, T. (2019). Computing solutions of the multiclass network equilibrium problem with affine cost functions. Annals of Operations Research, 274(1), 447–469.

    Google Scholar 

  41. Nash, J. F. (1951). Non-cooperative games. Annals of Mathematics, 54(2), 286–295.

    Google Scholar 

  42. Powell, W. B., & Sheffi, Y. (1982). The convergence of equilibrium algorithms with predetermined step sizes. Transportation Science, 16(1), 45–55.

    Google Scholar 

  43. Rath, K. P. (1992). A direct proof of the existence of pure strategy equilibria in games with a continuum of players. Economic Theory, 2(3), 427–433.

    Google Scholar 

  44. Raveau, S., Muñoz, J. C., & De Grange, L. (2011). A topological route choice model for metro. Transportation Research Part A: Policy and Practice, 45(2), 138–147.

    Google Scholar 

  45. Rosenthal, R. W. (1973). A class of games possessing pure-strategy nash equilibria. International Journal of Game Theory, 2(1), 65–67.

    Google Scholar 

  46. Roughgarden, T., & Tardos, E. (2002). How bad is selfish routing? Journal of ACM, 49(2), 236–259.

    Google Scholar 

  47. Roughgarden, T. & Tardos, E. ( 2004). Bouding the inefficiency of equilibria in nonatomic congestion games. In Games and Economic Behavior (pp. 389–403).

  48. Sandholm, W. H. (2001). Potential games with continuous player sets. Journal of Economic Theory, 97(1), 81–108.

    Google Scholar 

  49. Schmeidler, D. (1973). Equilibrium points of nonatomic games. Journal of Statistical Physics, 7(4), 295–300.

    Google Scholar 

  50. Sun, L., Lu, Y., Jin, J. G., Lee, D. H., & Axhausen, K. W. (2015). An integrated Bayesian approach for passenger flow assignment in metro networks. Transportation Research Part C: Emerging Technologies, 52, 116–131.

    Google Scholar 

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

    Google Scholar 

  52. Von Neumann, J., & Morgenstern, O. (1953). The theory of games and economic behavior. Princeton: Princeton University Press.

    Google Scholar 

  53. Wardrop, J. G. (1952). Some theoretical aspects of road traffic research. Proceedings of the Institute of Civil Engineers, 1(11), 325–378.

    Google Scholar 

  54. Yang, L., & Lam, W. (2006). Probit-type reliability-based transit network assignment. Transportation Research Record: Journal of the Transportation Research Board, 1977, 154–163.

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2021R1A2C1011341). The authors give their thanks to Eric Hong for his translation and proofreading. The authors are also grateful to Max Kapur for his proofreading and helpful suggestions for revision of the paper.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Suk-Joon Ko.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

A BNN and best-response dynamics

A BNN and best-response dynamics

For current aggregate choice x \(\in \) X, the \(x_i\) of each alternative i \(\in \) N can be disaggregated into \(x_i(\gamma )\), the portions from \(\gamma \in {\hat{\Gamma }}\): \(x_i\) \(=\) \(\sum _{\gamma \in {\hat{\Gamma }}} x_i(\gamma )\), i \(\in \) N. We define a response function \(r_i(x; \gamma )\) and step size \(\lambda (x; \gamma )\) so that the next point \(x'_i\) is defined as \(x'_i(\gamma )\) \(=\) \(x_i(\gamma )\) \(+\) \(\lambda (x;\gamma ) \left( r_i(x; \gamma ) - x_i(\gamma )\right) \). The Brown-von Neumann-Nash (BNN) dynamics use \(r_i(x;\gamma ) = {\hat{g}}(\gamma ) \frac{p_i(x; \gamma )}{\sum _{j \in N} p_j(x; \gamma )}\), and \(\lambda (x ; \gamma ) = \frac{\sum _{j \in N} p_j(x;\gamma )}{1+\sum _{j \in N} p_j(x;\gamma )}\), where \(p_i(x ; \gamma ) = \max \left\{ \frac{1}{{\hat{g}}(\gamma )}\sum _{j \in N} x_j(\gamma ) u_j(x ; \gamma ) -u_i(x; \gamma ), 0\right\} \). On the other hand, the best-response dynamics consider the set \(S(x;\gamma )\) of alternatives with the minimum disutility for \(\gamma \). For simplicity, write S \(\equiv \) \(S(x;\gamma )\) hereafter. Let \(r_i(x; \gamma )\) \(=\) \({\tilde{\rho }}_i(\gamma )\) if \(i \in S\) or 0 otherwise, where \({\tilde{\rho }}(\gamma )\) is generated randomly from the simplices \(\{\rho (\gamma ): \sum _{i \in S} \rho _i(\gamma ) = {\hat{g}}(\gamma )\), \(\rho _i(\gamma ) \ge 0\}\) for \(\gamma \) \(\in \) \({\hat{\Gamma }}\). We adopted the usual moderated step-size rule \(\lambda _k = \frac{1}{k+1}\) (see e.g. Fisk (1980)). In both dynamics, we hired stopping criterion \(\Vert x- x'\Vert \) < \(\epsilon \Vert x\Vert \) for \(\epsilon = 0.01\).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hong, SP., Kim, K.M. & Ko, SJ. Estimating heterogeneous agent preferences by inverse optimization in a randomized nonatomic game. Ann Oper Res 307, 207–228 (2021). https://doi.org/10.1007/s10479-021-04270-2

Download citation

Keywords

  • Nonatomic externality game
  • Taste heterogeneity
  • Taste-parameter randomization
  • Biquadratic inverse optimization