Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing

H.P. Stehouwer, E.H.L. Aarts, J. Wessels

Research output: Book/ReportBookScientific

Abstract

We present a neural network approach to the problem of determining lot sizes under demand uncertainty. The situation is considered in which at any decision moment the demand is given for a small finite data horizon into the future and the lot sizes are determined on a rolling-horizon basis. We demonstrate how a properly designed multi-layered perceptron can successfully be learned to detect planning horizons in case of a simple lot-sizing problem with Wagner-Whitin cost structure. We develop a two-stage decision procedure in which in the first stage the multi-layered perceptron estimates a planning horizon within the data horizon. In the second stage a detailed plan for this estimated planning horizon is calculated. We compare the cost performance of this procedure with some of the well-known lot-sizing heuristics for a number of different cost and demand conditions. The main finding is that the proposed approach is quite robust and dominates under the majority of the conditions.
Original languageEnglish
Place of PublicationEindhoven
PublisherTechnische Universiteit Eindhoven
Publication statusPublished - 1996
Externally publishedYes

Publication series

NameMemorandum COSOR

Fingerprint

Neural networks
Planning
Costs
Uncertainty

Cite this

Stehouwer, H. P., Aarts, E. H. L., & Wessels, J. (1996). Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing. (Memorandum COSOR). Eindhoven: Technische Universiteit Eindhoven.
Stehouwer, H.P. ; Aarts, E.H.L. ; Wessels, J. / Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing. Eindhoven : Technische Universiteit Eindhoven, 1996. (Memorandum COSOR).
@book{7df06f39354c436d9850ba81db532b1e,
title = "Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing",
abstract = "We present a neural network approach to the problem of determining lot sizes under demand uncertainty. The situation is considered in which at any decision moment the demand is given for a small finite data horizon into the future and the lot sizes are determined on a rolling-horizon basis. We demonstrate how a properly designed multi-layered perceptron can successfully be learned to detect planning horizons in case of a simple lot-sizing problem with Wagner-Whitin cost structure. We develop a two-stage decision procedure in which in the first stage the multi-layered perceptron estimates a planning horizon within the data horizon. In the second stage a detailed plan for this estimated planning horizon is calculated. We compare the cost performance of this procedure with some of the well-known lot-sizing heuristics for a number of different cost and demand conditions. The main finding is that the proposed approach is quite robust and dominates under the majority of the conditions.",
author = "H.P. Stehouwer and E.H.L. Aarts and J. Wessels",
year = "1996",
language = "English",
series = "Memorandum COSOR",
publisher = "Technische Universiteit Eindhoven",

}

Stehouwer, HP, Aarts, EHL & Wessels, J 1996, Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing. Memorandum COSOR, Technische Universiteit Eindhoven, Eindhoven.

Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing. / Stehouwer, H.P.; Aarts, E.H.L.; Wessels, J.

Eindhoven : Technische Universiteit Eindhoven, 1996. (Memorandum COSOR).

Research output: Book/ReportBookScientific

TY - BOOK

T1 - Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing

AU - Stehouwer, H.P.

AU - Aarts, E.H.L.

AU - Wessels, J.

PY - 1996

Y1 - 1996

N2 - We present a neural network approach to the problem of determining lot sizes under demand uncertainty. The situation is considered in which at any decision moment the demand is given for a small finite data horizon into the future and the lot sizes are determined on a rolling-horizon basis. We demonstrate how a properly designed multi-layered perceptron can successfully be learned to detect planning horizons in case of a simple lot-sizing problem with Wagner-Whitin cost structure. We develop a two-stage decision procedure in which in the first stage the multi-layered perceptron estimates a planning horizon within the data horizon. In the second stage a detailed plan for this estimated planning horizon is calculated. We compare the cost performance of this procedure with some of the well-known lot-sizing heuristics for a number of different cost and demand conditions. The main finding is that the proposed approach is quite robust and dominates under the majority of the conditions.

AB - We present a neural network approach to the problem of determining lot sizes under demand uncertainty. The situation is considered in which at any decision moment the demand is given for a small finite data horizon into the future and the lot sizes are determined on a rolling-horizon basis. We demonstrate how a properly designed multi-layered perceptron can successfully be learned to detect planning horizons in case of a simple lot-sizing problem with Wagner-Whitin cost structure. We develop a two-stage decision procedure in which in the first stage the multi-layered perceptron estimates a planning horizon within the data horizon. In the second stage a detailed plan for this estimated planning horizon is calculated. We compare the cost performance of this procedure with some of the well-known lot-sizing heuristics for a number of different cost and demand conditions. The main finding is that the proposed approach is quite robust and dominates under the majority of the conditions.

M3 - Book

T3 - Memorandum COSOR

BT - Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing

PB - Technische Universiteit Eindhoven

CY - Eindhoven

ER -

Stehouwer HP, Aarts EHL, Wessels J. Learning to detect planning horizons with multi-layered perceptrons : a case study for lot-sizing. Eindhoven: Technische Universiteit Eindhoven, 1996. (Memorandum COSOR).