Neural Demand Estimation with Habit Formation and Rationality Constraints
This work addresses demand estimation for economists and marketers by providing a flexible, non-parametric method that improves accuracy in predicting consumer behavior, though it is incremental in combining neural networks with economic constraints.
The authors tackled demand estimation by developing a neural demand system that incorporates habit formation and rationality constraints, achieving a 33% reduction in out-of-sample error and increasing welfare losses by 15-16% compared to static models.
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 .