Constrained Recursive Logit for Route Choice Analysis

2025-09-01

AI Summary

Traditional recursive logit (RL) models, though widely adopted, fail to exclude infeasible paths violating real-world constraints—such as time or energy budgets—thereby compromising behavioral realism. To address this, we propose a constrained recursive logit model that explicitly incorporates hard feasibility constraints into the RL framework for the first time. Our method restores Markovity via state-space augmentation, ensuring existence and uniqueness of the solution and numerical stability in estimation. We further design a value-iteration algorithm tailored to nonnegative discrete costs, enabling efficient, path-sampling-free parameter estimation with theoretical convergence guarantees. Experiments on synthetic networks and real-world transportation datasets demonstrate that the proposed model significantly improves both behavioral plausibility and estimation stability—particularly in complex, cyclic networks where conventional RL models suffer from path explosion and constraint violation.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The recursive logit (RL) model has become a widely used framework for route choice modeling, but it suffers from a key limitation: it assigns nonzero probabilities to all paths in the network, including those that are unrealistic, such as routes exceeding travel time deadlines or violating energy constraints. To address this gap, we propose a novel Constrained Recursive Logit (CRL) model that explicitly incorporates feasibility constraints into the RL framework. CRL retains the main advantages of RL-no path sampling and ease of prediction-but systematically excludes infeasible paths from the universal choice set. The model is inherently non-Markovian; to address this, we develop a tractable estimation approach based on extending the state space, which restores the Markov property and enables estimation using standard value iteration methods. We prove that our estimation method admits a unique solution under positive discrete costs and establish its equivalence to a multinomial logit model defined over restricted universal path choice sets. Empirical experiments on synthetic and real networks demonstrate that CRL improves behavioral realism and estimation stability, particularly in cyclic networks.

Problem

• Incorporates feasibility constraints into route choice modeling
• Excludes unrealistic paths from universal choice sets
• Enables tractable estimation with extended state space

Innovation

• Constrained Recursive Logit model with feasibility constraints
• State space extension restores Markov property
• Tractable estimation using standard value iteration methods