Scalable Dynamic Pricing of Substitutable Products through Structure-Guided Policy Learning
Abstract
Problem definition: We study dynamic pricing of substitutable products with finite, product-specific inventories. Customer substitution couples pricing decisions across products, while the inventory state makes exact dynamic programming intractable at realistic scale. Methodology / results: We develop two MNL-guided policy-learning approaches that replace the dynamic program with a statistical mapping from inventory states to pricing decisions. The first learns prices directly, while the second learns inventory opportunity costs and converts them into prices using the optimal MNL pricing rule. Both policies are trained using decision-focused learning. We also propose an efficient method to generate anticipative customer-choice targets to train our policies. Managerial implications: We conduct an extensive numerical evaluation of our approaches. On small instances for which the optimal dynamic program can be computed, the learned policies achieve average optimality gaps below 0.4%. On larger airline-motivated instances, they consistently improve on the tested revenue-management benchmarks. The comparison between the two architectures also highlights the role of model structure: using the MNL pricing characterization is particularly effective when demand is well described by MNL, while directly learning prices provides greater flexibility under heterogeneous mixed-MNL demand.
Related
- Scalable Pontryagin-Guided Adjoint-to-Control Recovery for Constrained Dynamic Portfolio Choice
- Coded Computing for Dynamic System via Cartesian Products
- Inferring geometric structure from eigenfunction triple products
- Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions
- Scalable Multi-Task Inverse Reinforcement Learning
BibTeX
@misc{su2026scalable,
title = {{Scalable Dynamic Pricing of Substitutable Products through Structure-Guided Policy Learning}},
author = {Yue Su and Antoine Désir and Axel Parmentier},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24605},
eprint = {2609.24605},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24605},
}
RIS
TY - UNPB
TI - Scalable Dynamic Pricing of Substitutable Products through Structure-Guided Policy Learning
AU - Yue Su
AU - Antoine Désir
AU - Axel Parmentier
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24605
UR - https://arxiv.org/abs/2609.24605
AB - Problem definition: We study dynamic pricing of substitutable products with finite, product-specific inventories. Customer substitution couples pricing decisions across products, while the inventory state makes exact dynamic programming intractable at realistic scale. Methodology / results: We develop two MNL-guided policy-learning approaches that replace the dynamic program with a statistical mapping from inventory states to pricing decisions. The first learns prices directly, while the second learns inventory opportunity costs and converts them into prices using the optimal MNL pricing rule. Both policies are trained using decision-focused learning. We also propose an efficient method to generate anticipative customer-choice targets to train our policies. Managerial implications: We conduct an extensive numerical evaluation of our approaches. On small instances for which the optimal dynamic program can be computed, the learned policies achieve average optimality gaps below 0.4%. On larger airline-motivated instances, they consistently improve on the tested revenue-management benchmarks. The comparison between the two architectures also highlights the role of model structure: using the MNL pricing characterization is particularly effective when demand is well described by MNL, while directly learning prices provides greater flexibility under heterogeneous mixed-MNL demand.
ER -