Neural-Bayesian Structure Learning for Discrete Choice Modeling
Summary
This paper proposes Neural-Bayesian Structure Learning, a framework that integrates differentiable structure learning with discrete choice modeling to predict choice behavior and evaluate interventions, achieving comparable performance while recovering coherent dependency structures.
View Cached Full Text
Cached at: 08/27/26, 09:37 AM
# Neural-Bayesian Structure Learning for Discrete Choice Modeling Source: [https://arxiv.org/abs/2608.25258](https://arxiv.org/abs/2608.25258) [View PDF](https://arxiv.org/pdf/2608.25258) > Abstract:Conventional discrete choice and machine learning models are estimated primarily from observational data and typically treat explanatory covariates as parallel inputs, providing no internal mechanism for determining how related attributes should adjust when one is deliberately changed\. This paper proposes Neural\-Bayesian Structure Learning \(Neural\-BSL\), a framework coupling differentiable structure learning with random\-utility\-based discrete choice estimation in a single differentiable procedure\. To prevent mutually exclusive choice outcome from distorting the recovered attribute structure, the observed choice is maintained outside the graph as an alternative\-specific utility comparison, while the attribute structure and random\-utility parameters are learned jointly\. The learned structure enters the choice model through structure\-weighted attribute interactions and provides the structural basis for propagating interventions through downstream attributes\. An intervention is evaluated by updating the intervened attribute, propagating its model\-implied downstream changes in topological order, and then recomputing utilities and choice probabilities\. This yields both predicted mode\-share responses and the associated changes in downstream traveler or trip attributes\. We evaluate Neural\-BSL using stated\-preference data from Seoul and the revealed\-preference data from London\. Neural\-BSL achieves predictive performance comparable to conventional benchmarks while recovering behaviorally coherent dependency structures\. Across policy scenarios, propagating interventions through the learned structure changes the predicted redistribution across modes while exposing the downstream traveler and trip adjustments underlying those responses\. ## Submission history From: Eui\-Jin Kim \[[view email](https://arxiv.org/show-email/3302afe0/2608.25258)\] **\[v1\]**Wed, 26 Aug 2026 00:42:54 UTC \(2,105 KB\)
Similar Articles
An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks
This paper evaluates four machine learning models for discrete choice modeling in policy preference elicitation, using Monte Carlo experiments and a real energy policy case study to assess performance under individual heterogeneity and choice complexity.
Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
DyStruct is a training-free Bayesian decoding framework for discrete Diffusion Language Models that enables flexible-length generation by dynamically determining expansion size and decoding order, improving accuracy on math and code tasks.
Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
This paper proposes a two-stage adapter that embeds foundation model predictions into a multinomial logit model, preserving economic properties like cost monotonicity and interpretable willingness-to-pay while improving accuracy by up to 12.8 percentage points.
Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach
Proposes a hierarchical Bayesian framework for meta-learning in dynamical systems from multiple sparse, noisy datasets, using gradient-based MCMC with an embedded ODE solver for efficient posterior inference of shared and dataset-specific parameters.
Structured Reinforcement Learning for Bayesian Persuasion : Application to Intelligent Interactive Driving
This paper proposes a structured reinforcement learning framework for Bayesian persuasion in interactive driving, where a lead vehicle selectively reveals traffic information to guide connected vehicles. The method introduces MAPL and SQP algorithms, achieving 30% cost efficiency over existing methods.