Integrable Elasticity via Neural Demand Potentials
For retail demand modeling, the paper introduces a neural method that ensures integrability and produces more reliable cross-price elasticity estimates.
The paper proposes the Integrable Context-Dependent Demand Network (ICDN) for multiproduct retail demand, which learns log-demand as a smooth function of log-prices to derive exact elasticities. On the Dominick's beer dataset, ICDN improves out-of-sample generalization over a log-log benchmark and yields more stable, economically plausible elasticity estimates.
We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-demand as a smooth, context-conditioned function of log-prices, allowing elasticities to be derived exactly from the learned demand surface. On the Dominick's beer dataset, ICDN improves out-of-sample generalization over a directed log-log benchmark and yields more stable, economically plausible elasticity estimates, especially for weakly identified cross-price effects.