Evaluation of forecasting approaches using hybrid multicriteria decision-making models

Badulescu, Yvonne (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale ; University of Lausanne, Switzerland) ; Cheikhrouhou, Naoufel (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale)

The demand forecast is the most influential input into enterprise activities planning thus creating a challenging issue for Demand Planning experts in model selection. Models including quantitative, qualitative and hybrid forecasting methods have been developed and are widely used. The literature reveals the use of several case-dependent error measures to evaluate forecasting accuracy, however, these performance indicators may at times differentiate in results making it more difficult in determining the most appropriate forecasting model for the users’ needs. This paper presents the development of two hybrid multi-criteria decision making approaches, AHP-TOPSIS and ANP-TOPSIS, to evaluate and rank the relative performances based on error measures of alternate forecasting models. Validation is provided through an industrial application using empirical data from a plastic bag manufacturer based on five models


Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG - Genève
Institute:
CRAG - Centre de Recherche Appliquée en Gestion
Subject(s):
Economie/gestion
Publisher:
Granada, Spain, 19-21 September 2018
Date:
2018-09
Granada, Spain
19-21 September 2018
Pagination:
12 p.
Published in:
Proceedings of International Conference on Time Series and Forecasting (ITISE 2018)
Appears in Collection:



 Record created 2018-10-11, last modified 2019-06-11

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)