Neural Demand Estimation with Habit Formation and Rationality Constraints

TL;DR

This paper introduces a neural demand estimation model incorporating habit formation and rationality constraints, improving accuracy and welfare analysis in demand systems without relying on parametric utility functions.

Contribution

It presents a novel neural demand system that estimates demand shares with regularity constraints and habit dependence, enhancing flexibility and interpretability over traditional models.

Findings

Simulations accurately recover elasticities and welfare effects.

Adding habit reduces out-of-sample error by approximately 33%.

Habit formation significantly alters substitution patterns and welfare estimates.

Abstract

We develop a flexible neural demand system for continuous budget allocation that estimates budget shares on the simplex by minimizing KL divergence. Shares are produced via a softmax of a state-dependent preference scorer and disciplined with regularity penalties (monotonicity, Slutsky symmetry) to support coherent comparative statics and welfare without imposing a parametric utility form. State dependence enters through a habit stock defined as an exponentially weighted moving average of past consumption. Simulations recover elasticities and welfare accurately and show sizable gains when habit formation is present. In our empirical application using Dominick's analgesics data, adding habit reduces out-of-sample error by c.33%, reshapes substitution patterns, and increases CV losses from a 10% ibuprofen price rise by about 15-16% relative to a static model. The code is available at https://github.com/martagrz/neural_demand_habit .