Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yi, Chen, Elynn, Yan, Yujun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912665491734528
author Zhang, Yi
Chen, Elynn
Yan, Yujun
author_facet Zhang, Yi
Chen, Elynn
Yan, Yujun
contents We study contextual dynamic pricing when a target market can leverage K auxiliary markets -- offline logs or concurrent streams -- whose mean utilities differ by a structured preference shift. We propose Cross-Market Transfer Dynamic Pricing (CM-TDP), the first algorithm that provably handles such model-shift transfer and delivers minimax-optimal regret for both linear and non-parametric utility models. For linear utilities of dimension d, where the difference between source- and target-task coefficients is $s_{0}$-sparse, CM-TDP attains regret $\tilde{O}((d*K^{-1}+s_{0})\log T)$. For nonlinear demand residing in a reproducing kernel Hilbert space with effective dimension $α$, complexity $β$ and task-similarity parameter $H$, the regret becomes $\tilde{O}\!(K^{-2αβ/(2αβ+1)}T^{1/(2αβ+1)} + H^{2/(2α+1)}T^{1/(2α+1)})$, matching information-theoretic lower bounds up to logarithmic factors. The RKHS bound is the first of its kind for transfer pricing and is of independent interest. Extensive simulations show up to 50% lower cumulative regret and 5 times faster learning relative to single-market pricing baselines. By bridging transfer learning, robust aggregation, and revenue optimization, CM-TDP moves toward pricing systems that transfer faster, price smarter.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
Zhang, Yi
Chen, Elynn
Yan, Yujun
Methodology
Machine Learning
Applications
We study contextual dynamic pricing when a target market can leverage K auxiliary markets -- offline logs or concurrent streams -- whose mean utilities differ by a structured preference shift. We propose Cross-Market Transfer Dynamic Pricing (CM-TDP), the first algorithm that provably handles such model-shift transfer and delivers minimax-optimal regret for both linear and non-parametric utility models. For linear utilities of dimension d, where the difference between source- and target-task coefficients is $s_{0}$-sparse, CM-TDP attains regret $\tilde{O}((d*K^{-1}+s_{0})\log T)$. For nonlinear demand residing in a reproducing kernel Hilbert space with effective dimension $α$, complexity $β$ and task-similarity parameter $H$, the regret becomes $\tilde{O}\!(K^{-2αβ/(2αβ+1)}T^{1/(2αβ+1)} + H^{2/(2α+1)}T^{1/(2α+1)})$, matching information-theoretic lower bounds up to logarithmic factors. The RKHS bound is the first of its kind for transfer pricing and is of independent interest. Extensive simulations show up to 50% lower cumulative regret and 5 times faster learning relative to single-market pricing baselines. By bridging transfer learning, robust aggregation, and revenue optimization, CM-TDP moves toward pricing systems that transfer faster, price smarter.
title Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
topic Methodology
Machine Learning
Applications
url https://arxiv.org/abs/2505.17203