Confidence Intervals for Data-Driven Inventory Policies with Demand Censoring

Forthcoming in Operations Research

47 Pages Posted: 4 Sep 2015 Last revised: 17 Jun 2019

Date Written: April 20, 2019

Abstract

We revisit the classical dynamic inventory management problem of Scarf (1959) from the perspective of a decision-maker who has n historical selling seasons of data and must make ordering decisions for the upcoming season. We develop a nonparametric estimation procedure for the (S, s) policy that is consistent, then characterize the finite-sample properties of the estimated (S, s) levels by deriving their asymptotic confidence intervals. We also consider having at least some of the past selling seasons of data censored from the absence of backlogging, and show that the intuitive procedure of first correcting for censoring in the demand data yields inconsistent estimates. We then show how to correctly use the censored data to obtain consistent estimates and derive asymptotic confidence intervals for this policy using Stein's method. We further show the confidence intervals can be used to effectively bound the difference between the expected total cost of an estimated policy and that of the optimal policy. We validate our results with extensive computations on simulated data. Our results extend to the repeated newsvendor problem and the base-stock policy problem by appropriate parameter choices.

Keywords: demand censoring, inventory management, estimation, nonparametric, dynamic programming

Suggested Citation

Ban, Gah‐Yi, Confidence Intervals for Data-Driven Inventory Policies with Demand Censoring (April 20, 2019). Forthcoming in Operations Research . Available at SSRN: https://ssrn.com/abstract=2654014 or http://dx.doi.org/10.2139/ssrn.2654014

Gah‐Yi Ban (Contact Author)

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
662
Abstract Views
2,300
rank
38,801
PlumX Metrics