Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence
Abstract
Feature-based multi-product pricing uses customer characteristics to identify demand heterogeneity and tailor prices across products. Choice model trees segment customers through interpretable feature rules and fit a demand model within each leaf. Existing methods typically construct these trees greedily, selecting one myopic split at a time. We develop optimal choice model trees with multinomial logit leaves (OCMT-MNL), jointly optimizing the tree and leaf models within a prescribed depth. Our exact dynamic program derives closed-form Fenchel lower bounds during constrained Newton iterations and propagates them across nested and disjoint customer subsets, avoiding new fits and resuming unfinished fits without repeating completed work. In synthetic experiments, it reduces exact leaf fits by 99.98% and leaf evaluations by 86.13%, achieving up to 7.15-fold speedups over unpruned dynamic programming. One-dimensional lookup tables translate offline estimation into real-time pricing, with a revenue-loss bound quadratic in grid spacing under the fitted model. Compared with greedy trees, OCMT-MNL achieves lower revenue loss with fewer leaves on synthetic data and better predictive fit on real data. In a 23-week randomized experiment on ancillary seat pricing across 48 airline markets and 190,220 passengers, OCMT-MNL increases seat revenue per passenger by a statistically significant 11.3% over static pricing.
Related
- HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
- Learning from Historical Transactions: Robust Supplier Pricing and Stocking with Sparse Data
- Oblivious Learning and Collusive Pricing
- Scalable Dynamic Pricing of Substitutable Products through Structure-Guided Policy Learning
- Finance-Informed Operator Learning for Option Pricing with Quantum-Compatible Realizations
BibTeX
@misc{zhang2026learning,
title = {{Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence}},
author = {Jiajie Zhang and Yanqiu Ruan and Xiao Jin and Chung Piaw Teo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.16952},
eprint = {2609.16952},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.16952},
}
RIS
TY - UNPB
TI - Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence
AU - Jiajie Zhang
AU - Yanqiu Ruan
AU - Xiao Jin
AU - Chung Piaw Teo
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.16952
UR - https://arxiv.org/abs/2609.16952
AB - Feature-based multi-product pricing uses customer characteristics to identify demand heterogeneity and tailor prices across products. Choice model trees segment customers through interpretable feature rules and fit a demand model within each leaf. Existing methods typically construct these trees greedily, selecting one myopic split at a time. We develop optimal choice model trees with multinomial logit leaves (OCMT-MNL), jointly optimizing the tree and leaf models within a prescribed depth. Our exact dynamic program derives closed-form Fenchel lower bounds during constrained Newton iterations and propagates them across nested and disjoint customer subsets, avoiding new fits and resuming unfinished fits without repeating completed work. In synthetic experiments, it reduces exact leaf fits by 99.98% and leaf evaluations by 86.13%, achieving up to 7.15-fold speedups over unpruned dynamic programming. One-dimensional lookup tables translate offline estimation into real-time pricing, with a revenue-loss bound quadratic in grid spacing under the fitted model. Compared with greedy trees, OCMT-MNL achieves lower revenue loss with fewer leaves on synthetic data and better predictive fit on real data. In a 23-week randomized experiment on ancillary seat pricing across 48 airline markets and 190,220 passengers, OCMT-MNL increases seat revenue per passenger by a statistically significant 11.3% over static pricing.
ER -