Training Neural Networks Embedded in Dynamic Discrete Choice Models
Authors:
- Ecenur OguzEOEcenur Oguz
- Robert BrayRBRobert Bray
Preprint
- 20 April 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
We develop the first general-purpose estimator for infinite-horizon dynamic discrete choice models whose estimation problem, after pre-computation, is unencumbered by large systems of linear equations-either imposed as constraints, or embedded in the objective function. Our unnested fixed point (UFXP) and optimal unnested fixed point (OUFXP) estimators exploit a dual representation of Bellman's equation to separate the utility parameters from the dynamic programming fixed point. We establish the consistency and asymptotic normality of UFXP and OUFXP, as well as the efficiency of the latter. Our estimators enable researchers to model utility functions non-parametrically via flexible neural-network approximations.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A neural-embedded discrete choice model: Learning taste representation with strengthened interpretabilityTransportation Research Part B: Methodological, 2022
- Choice modelling in the age of machine learning - Discussion paperJournal of Choice Modelling, 2022
- Enhancing discrete choice models with representation learningTransportation Research Part B: Methodological, 2020
- Dynamic discrete choice structural models: A surveyJournal of Econometrics, 2010
- Microeconometrics2005
- Swapping the Nested Fixed Point Algorithm: A Class of Estimators for Discrete Markov Decision ModelsEconometrica, 2002
- The Dynamics of Markups and Inventories in Retailing FirmsReview of Economic Studies, 1999
- Chapter 51 Structural estimation of markov decision processes1994
- Chapter 36 Large sample estimation and hypothesis testing1994
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989