A decomposition method for estimating recursive logit based route choice models

Research Paper

Abstract

Fosgerau et al. (2013) recently proposed the recursive logit (RL) model for route choice problems, that can be consistently estimated and easily used for prediction without any sampling of choice sets. Its estimation however requires solving many large-scale systems of linear equations, which can be computationally costly for real data sets. We design a decomposition (DeC) method in order to reduce the number of linear systems to be solved, opening the possibility to estimate more complex RL based models, for instance mixed RL models. We test the performance of the DeC method by estimating the RL model on two networks of more than 7000 and 40,000 links, and we show that the DeC method significantly reduces the estimation time. We also use the DeC method to estimate two mixed RL specifications, one using random coefficients and one incorporating error components associated with subnetworks (Frejinger and Bierlaire 2007). The models are estimated on a real network and a cross-validation study is performed. The results suggest that the mixed RL models can be estimated in a reasonable time with the DeC method. These models yield sensible parameter estimates and the in-sample and out-of sample fits are significantly better than the RL model.

Keywords

Decomposition method Route choice Mixed recursive logit models Subnetworks Cross-validation 

References

  1. Bastin F, Cirillo C, Toint PhL (2006) Convergence theory for nonconvex stochastic programming with an application to mixed logit. Math Program Ser B 108(2–3):207–234CrossRefGoogle Scholar
  2. Bekhor S, Ben-Akiva M, Ramming M (1805) Adaptation of logit kernel to route choice situation. Transp Res Record 78–85:2002Google Scholar
  3. Ben-Akiva M, Bierlaire M (1999) Discrete choice methods and their applications to short-term travel decisions. In: Hall R (ed.) Handbook of Transportation Science, pp 5–34. KluwerGoogle Scholar
  4. Ben-Akiva M (1973) The structure of travel demand models. PhD thesis, MITGoogle Scholar
  5. Bolduc D, Ben-Akiva M (1991) A multinomial probit formulation for large choice sets. In: Proceedings of the 6th International Conference on Travel Behaviour, vol 2, pp 243–258Google Scholar
  6. Broyden CG (1970) The convergence of a class of double-rank minimization algorithms 1. General considerations. IMA J Appl Math 6(1):76–90CrossRefGoogle Scholar
  7. Fletcher R (1970) A new approach to variable metric algorithms. Comput J 13(3):317–322CrossRefGoogle Scholar
  8. Fosgerau M, Frejinger E, Karlström A (2013) A link based network route choice model with unrestricted choice set. Transp Res Part B 56:70–80CrossRefGoogle Scholar
  9. Frejinger E, Bierlaire M, Ben-Akiva M (2009) Sampling of alternatives for route choice modeling. Transp Res Part B 43(10):984–994CrossRefGoogle Scholar
  10. Frejinger E, Bierlaire M (2007) Capturing correlation with subnetworks in route choice models. Transp Res Part B 41(3):363–378CrossRefGoogle Scholar
  11. Goldfarb D (1970) A family of variable metric updates derived by variational means. Math Comput 24(109):23–26CrossRefGoogle Scholar
  12. Lai X, Bierlaire M (2015) Specification of the cross nested logit model with sampling of alternatives for route choice models. Transp Res Part B 80:220–234CrossRefGoogle Scholar
  13. Mai T (2016) A method of integrating correlation structures for a generalized recursive route choice model. Transp Res Part B 93(1):146–161CrossRefGoogle Scholar
  14. Mai T, Fosgerau M, Frejinger E (2015a) A nested recursive logit model for route choice analysis. Transp Res Part B 75(1):100–112CrossRefGoogle Scholar
  15. Mai T, Frejinger E, Bastin F (2015b) A misspecification test for logit based route choice models. Econ Transp 4(4):215–226CrossRefGoogle Scholar
  16. McFadden D (1978) Modelling the choice of residential location. In: Karlqvist A, Lundqvist L, Snickars F, Weibull J (eds) Spatial Interaction Theory and Residential Location. North-Holland, Amsterdam, pp 75–96Google Scholar
  17. McFadden DL, Train K (2000) Mixed MNL models for discrete response. J Appl Econ 15(5):447–470CrossRefGoogle Scholar
  18. Munger D, L’Ecuyer P, Bastin F, Cirillo C, Tuffin B (2012) Estimation of the mixed logit likelihood function by randomized quasi-monte carlo. Transp Res Part B 46(2):305–320CrossRefGoogle Scholar
  19. Nocedal J, Wright SJ (2006) Numer Optim, 2nd edn. Springer, New York, NY, USAGoogle Scholar
  20. Rust J (1987) Optimal replacement of GMC bus engines: an empirical model of Harold Zurcher. Econometrica 55(5):999–1033CrossRefGoogle Scholar
  21. Shanno DF (1970) Conditioning of quasi-Newton methods for function minimization. Math Comput 24(111):647–656CrossRefGoogle Scholar
  22. Train K (2003) Discrete choice methods with simulation. Cambridge University PressGoogle Scholar
  23. Zimmermann M, Mai T, Frejinger E (2016) Bike route choice modeling using GPS data without choice sets of paths. CIRRELT-2016-49, Interuniversity Research Centre on Enterprise Networks, Logistics and TransportationGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg and EURO - The Association of European Operational Research Societies 2016

Authors and Affiliations

  1. 1.Department of Mathematical and Industrial EngineeringPolytechnique MontréalMontréalCanada
  2. 2.Department of Computer Science and Operations ResearchUniversité de Montréal and CIRRELTMontréalCanada

Personalised recommendations