A link based network route choice model with unrestricted choice set

Abstract

This paper considers the path choice problem, formulating and discussing an econometric random utility model for the choice of path in a network with no restriction on the choice set. Starting from a dynamic specification of link choices we show that it is equivalent to a static model of the multinomial logit form but with infinitely many alternatives. The model can be consistently estimated and used for prediction in a computationally efficient way. Similarly to the path size logit model, we propose an attribute called link size that corrects utilities of overlapping paths but that is link additive. The model is applied to data recording path choices in a network with more than 3,000 nodes and 7,000 links.

A Subpath-based Logit Model to Capture the Correlation of Routes

“…Besides, it would be useful to examine and discuss the appropriate size of the subpath in the CNL model. Moreover, the proposed idea can be applied with the DDR [14] or the recursive Logit [5] methods; therefore, the "data processing"-"choice set generation"-"route choice model" steps can be obtained at the same time, instead of doing them step-by-step. …”

“…Prato [4] provided a literature review on the most frequently used methodologies in route choice modelling. Recently, Fosgerau et al [5] proposed a recursive Logit model that does not require the enumeration of paths. Papola and Marzano [6] proposed a joint network generalized extreme value (GEV) approach to model the route choice that does not require choice set generation as well.…”

The valuation of travel-time variability

“…Another challenge is that we need to estimate models that describe route choice in large networks. A new generation of models is emerging (Fosgerau et al, 2013) that may be useful in this context. These new models resolve the issue that the number of possible routes in large networks is extremely large.…”

Operational route choice methodologies for practical applications

“…Akamatsu, 1996;Baillon and Cominetti, 2008), Fosgerau et al (2013) present the recursive logit (RL) model, where the path choice problem is formulated as a sequential link choice problem in a dynamic framework. The proposed technique avoids the full enumeration of paths and does not require sampling of alternatives.…”

“…Modeling route choice involves several challenges, pertaining to both data availability and accuracy, and model structure and computational efficiency. The main challenge related to the route choice problem, namely the generation of the choice set, has been circumvented by Fosgerau et al (2013) through a Markovian link choice problem that is equivalent to a path-based logit model. It is called the recursive logit (RL) model and it is directly applicable for analysis at a disaggregate level.…”