EconBase
← All papers

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

Jianyu Xu, Yu-Xiang Wang

arXiv 27 Jan 2022 · Machine Learning · 5 citations (OpenAlex)

arXiv:2201.11341 · PDF · DOI · OpenAlex · Extracted main text

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 $\tilde{\Theta}(d^{\frac13}T^{\frac23})$ minimax regret up to logarithmic factors. For the latter model, we present an algorithm that achieves an $\tilde{O}(T^{\frac34})$ regret, and improve the best-known lower bound from $\Omega(T^{\frac35})$ to $\tilde{\Omega}(T^{\frac23})$. 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.

Citation extraction

26
references
71
in-text mentions
26
distinct cited
2
self-citations
8,386
main-text words

appendix boundary found by appendix_command · 58% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Cohen, M. C., Lobel, I., and Paes Leme, R (2020) Feature-based dynamic pricing1.00083100%
2Auer, P., Cesa-Bianchi, N., Freund, Y., and Schapire, R. E (2002) The nonstochastic multiarmed bandit problem1.00053100%
3Wang, Y., Chen, B., and Simchi-Levi, D (2021) Multimodal dynamic pricing self0.9285480%
4Kleinberg, R (2004) Nearly tight bounds for the continuum-armed bandit problem0.92843100%
5Kleinberg, R. and Leighton, T (2003) The value of knowing a demand curve: Bounds on regret for online posted-price auctions0.87472100%
6Javanmard, A. and Nazerzadeh, H (2019) Dynamic pricing in high-dimensions0.87462100%
7Luo, Y., Sun, W. W., et al (2021) Distribution-free contextual dynamic pricing0.87462100%
8Xu, J. and Wang, Y.-X (2021) Logarithmic regret in feature-based dynamic pricing self0.84333100%
9Leme, R. P. and Schneider, J (2018) Contextual search via intrinsic volumes0.73732100%
10Liu, A., Leme, R. P., and Schneider, J (2021) Optimal contextual pricing and extensions0.73732100%

Showing the top 10 of 26 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand0.92096
2Doubly Fair Dynamic Pricing0.51132
3Policy Optimization Using Semi-parametric Models for Dynamic Pricing0.51121
4Pricing with Contextual Elasticity and Heteroscedastic Valuation0.00011