Dynamic pricing with finite price sets: a non-parametric approach
Dynamic pricing with finite price sets: a non-parametric approach
We study price optimization of perishable inventory over multiple, consecutive selling seasons in the presence of demand uncertainty. Each selling season consists of a finite number of discrete time periods, and demand per time period is Bernoulli distributed with price-dependent parameter. The set of feasible prices is finite, and the expected demand corresponding to each price is unknown to the seller, whose objective is to maximize cumulative expected revenue. We propose an algorithm that estimates the unknown parameters in a learning phase, and in each subsequent season applies a policy determined as the solution to a sample dynamic program, which modifies the underlying dynamic program by replacing the unknown parameters by the estimate. Revenue performance is measured by the regret: the expected revenue loss relative to the optimal attainable revenue under full information. For a given number of seasons n, we show that if the number of seasons allocated to learning is asymptotic to (n2logn)1/3, then the regret is of the same order, uniformly over all unknown demand parameters. An extensive numerical study that compares our algorithm to six benchmarks adapted from the literature demonstrates the effectiveness of our approach.
Asymptotic analysis, Dynamic pricing, Dynamic programming, Markov decision process, Regret
Avramidis, Athanasios
d6c4b6b6-c0cf-4ed1-bbe1-a539937e4001
den Boer, Arnoud
ec761202-becc-4c7e-aac4-abdc6da9caf3
28 June 2021
Avramidis, Athanasios
d6c4b6b6-c0cf-4ed1-bbe1-a539937e4001
den Boer, Arnoud
ec761202-becc-4c7e-aac4-abdc6da9caf3
Avramidis, Athanasios and den Boer, Arnoud
(2021)
Dynamic pricing with finite price sets: a non-parametric approach.
Mathematical Methods of Operations Research, 94 (1).
(doi:10.1007/s00186-021-00744-y).
Abstract
We study price optimization of perishable inventory over multiple, consecutive selling seasons in the presence of demand uncertainty. Each selling season consists of a finite number of discrete time periods, and demand per time period is Bernoulli distributed with price-dependent parameter. The set of feasible prices is finite, and the expected demand corresponding to each price is unknown to the seller, whose objective is to maximize cumulative expected revenue. We propose an algorithm that estimates the unknown parameters in a learning phase, and in each subsequent season applies a policy determined as the solution to a sample dynamic program, which modifies the underlying dynamic program by replacing the unknown parameters by the estimate. Revenue performance is measured by the regret: the expected revenue loss relative to the optimal attainable revenue under full information. For a given number of seasons n, we show that if the number of seasons allocated to learning is asymptotic to (n2logn)1/3, then the regret is of the same order, uniformly over all unknown demand parameters. An extensive numerical study that compares our algorithm to six benchmarks adapted from the literature demonstrates the effectiveness of our approach.
More information
Submitted date: 22 October 2018
Published date: 28 June 2021
Additional Information:
Publisher Copyright:
© 2021, The Author(s).
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
Keywords:
Asymptotic analysis, Dynamic pricing, Dynamic programming, Markov decision process, Regret
Identifiers
Local EPrints ID: 425539
URI: http://eprints.soton.ac.uk/id/eprint/425539
ISSN: 1432-2994
PURE UUID: 86a551d5-9256-4908-a90a-e7558e286ef7
Catalogue record
Date deposited: 24 Oct 2018 16:30
Last modified: 06 Jun 2024 01:45
Export record
Altmetrics
Contributors
Author:
Arnoud den Boer
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
