Paper Overview
Field: ML Authors: Carlos Heredia, Daniel Roncel Published: 2025-05-23 arXiv: 2505.17388
Abstract (translated)
We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multi-product retail demand forecasting. The model learns log-demand as a smooth, context-conditioned function of log-prices, from which elasticities can be derived exactly from the learned demand surface. On the Dominick's beer dataset, ICDN improves out-of-sample generalization over log-log baselines and produces more stable, economically plausible elasticity estimates, especially for weakly identified cross-price effects.
Key Points
- Introduces ICDN, a neural network designed so that price elasticities are integrable by construction.
- Models log-demand as a smooth function of log-prices, conditioned on context, enabling exact elasticity derivation rather than post-hoc estimation.
- Evaluated on the Dominick's beer dataset, showing improved out-of-sample generalization versus log-log regression baselines.
- Delivers more stable and economically reasonable elasticity estimates, notably for cross-price effects that are typically weakly identified.
*Auto-collected on 2026-05-23*