Neural-Bayesian Structure Learning for Discrete Choice Modeling
Read the original on arXiv Machine Learning →Neural-Bayesian Structure Learning (Neural-BSL) integrates differentiable structure learning with random-utility discrete choice estimation in a single differentiable framework. It keeps observed choices outside the graph to avoid distortion, learns attribute interactions through a structure-weighted network, and propagates interventions by updating attributes in topological order before recomputing utilities and choice probabilities. Evaluations on Seoul stated-preference and London revealed-preference data show Neural-BSL matches conventional benchmarks in predictive performance while uncovering behaviorally coherent dependency structures and revealing downstream traveler and trip adjustments under policy scenarios.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.