TY - JOUR
T1 - Nonparametric data-driven learning algorithms for multilocation inventory systems
AU - Zhong, Zijun
AU - He, Zhou
PY - 2024/11
Y1 - 2024/11
N2 - We study a multilocation inventory system with unknown demand distribution using a nonparametric approach. The system consists of multiple distribution centers and customer locations, where products are shipped from the distribution centers to fulfill customer demands. We propose a novel algorithm, DMLI, for adaptive inventory management. Under specific conditions, we establish that the average expected T-period regret of DMLI converges to the optimal rate of O(1/√T). © 2024 Elsevier B.V.
AB - We study a multilocation inventory system with unknown demand distribution using a nonparametric approach. The system consists of multiple distribution centers and customer locations, where products are shipped from the distribution centers to fulfill customer demands. We propose a novel algorithm, DMLI, for adaptive inventory management. Under specific conditions, we establish that the average expected T-period regret of DMLI converges to the optimal rate of O(1/√T). © 2024 Elsevier B.V.
KW - Multilocation inventory system
KW - Nonparametric learning
KW - Online convex optimization
KW - Regret
UR - http://www.scopus.com/inward/record.url?scp=85202343428&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85202343428&origin=recordpage
U2 - 10.1016/j.orl.2024.107163
DO - 10.1016/j.orl.2024.107163
M3 - RGC 21 - Publication in refereed journal
SN - 0167-6377
VL - 57
JO - Operations Research Letters
JF - Operations Research Letters
M1 - 107163
ER -