Learning Behavioral Parameters of Network Equilibrium Models from Aggregate Mobility Data
Abstract
Estimating travel behavior parameters is essential for understanding current travel patterns and for forecasting how travelers may respond to future changes in transportation systems. However, reliable estimation remains difficult when behavior must be inferred from sparse and aggregate observations, especially when jointly recovering several behavioral components. In this paper, we develop a bi-level estimation program for a combined destination, mode and route choice model with congestion. The inner level is a convex program at given scale parameters, and returns the taste coefficients as its dual variables together with the equilibrium travel pattern. The outer level selects the scale parameters by out-of-sample prediction, measured by how well the modeled travel pattern predicts observations withheld from estimation. To solve the bi-level problem at scale, we propose a matrix-free Hierarchical Lagrangian Dual algorithm as the inner solver and an outer search by implicit differentiation, which uses the sensitivities of the inner solution to enable efficient search over the scale parameters and reaches the calibrated scales in a handful of iterations. We validate the approach on Los Angeles County using public origin-destination, mode-share and traffic-count data. Our approach scales to a county-level problem with 2.7 million variables and substantially improves computational efficiency over a general-purpose conic solver. Compared with the fixed-scale benchmark, the calibrated model improves predictive performance at the destination and mode levels, with consistent gains across complementary goodness-of-fit measures.
Related
- Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
- Resolving the Mobility-Equity-Emissions Trilemma: A Causal Machine Learning Framework for Dynamic Tolling Policy
- Dynamic Spatial Bayesian Machine Learning Model: Applications to Intergenerational Economic Mobility and Geographic Income Inequality in the United States
- Personalized and differentially private federated learning for mobility data mining via the TrajectoryGuard framework
- Equilibrium Learning in Unbounded Stochastic Games with Gaussian Transitions
BibTeX
@misc{hong2026learning,
title = {{Learning Behavioral Parameters of Network Equilibrium Models from Aggregate Mobility Data}},
author = {Tenglong Hong and Youngseo Kim},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35723},
eprint = {2610.35723},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35723},
}
RIS
TY - UNPB
TI - Learning Behavioral Parameters of Network Equilibrium Models from Aggregate Mobility Data
AU - Tenglong Hong
AU - Youngseo Kim
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35723
UR - https://arxiv.org/abs/2610.35723
AB - Estimating travel behavior parameters is essential for understanding current travel patterns and for forecasting how travelers may respond to future changes in transportation systems. However, reliable estimation remains difficult when behavior must be inferred from sparse and aggregate observations, especially when jointly recovering several behavioral components. In this paper, we develop a bi-level estimation program for a combined destination, mode and route choice model with congestion. The inner level is a convex program at given scale parameters, and returns the taste coefficients as its dual variables together with the equilibrium travel pattern. The outer level selects the scale parameters by out-of-sample prediction, measured by how well the modeled travel pattern predicts observations withheld from estimation. To solve the bi-level problem at scale, we propose a matrix-free Hierarchical Lagrangian Dual algorithm as the inner solver and an outer search by implicit differentiation, which uses the sensitivities of the inner solution to enable efficient search over the scale parameters and reaches the calibrated scales in a handful of iterations. We validate the approach on Los Angeles County using public origin-destination, mode-share and traffic-count data. Our approach scales to a county-level problem with 2.7 million variables and substantially improves computational efficiency over a general-purpose conic solver. Compared with the fixed-scale benchmark, the calibrated model improves predictive performance at the destination and mode levels, with consistent gains across complementary goodness-of-fit measures.
ER -