ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2201.11341
59
20

Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise

27 January 2022
Jianyu Xu
Yu-Xiang Wang
ArXivPDFHTML
Abstract

In feature-based dynamic pricing, a seller sets appropriate prices for a sequence of products (described by feature vectors) on the fly by learning from the binary outcomes of previous sales sessions ("Sold" if valuation ≥\geq≥ price, and "Not Sold" otherwise). Existing works either assume noiseless linear valuation or precisely-known noise distribution, which limits the applicability of those algorithms in practice when these assumptions are hard to verify. In this work, we study two more agnostic models: (a) a "linear policy" problem where we aim at competing with the best linear pricing policy while making no assumptions on the data, and (b) a "linear noisy valuation" problem where the random valuation is linear plus an unknown and assumption-free noise. For the former model, we show a Θ~(d13T23)\tilde{\Theta}(d^{\frac13}T^{\frac23})Θ~(d31​T32​) minimax regret up to logarithmic factors. For the latter model, we present an algorithm that achieves an O~(T34)\tilde{O}(T^{\frac34})O~(T43​) regret, and improve the best-known lower bound from Ω(T35)\Omega(T^{\frac35})Ω(T53​) to Ω~(T23)\tilde{\Omega}(T^{\frac23})Ω~(T32​). These results demonstrate that no-regret learning is possible for feature-based dynamic pricing under weak assumptions, but also reveal a disappointing fact that the seemingly richer pricing feedback is not significantly more useful than the bandit-feedback in regret reduction.

View on arXiv
Comments on this paper