Fuzzy decision support system for demand forecasting with a learning mechanism

Dobrila Petrovic, Ying Xie, Keith Burnham

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

In this paper, a new decision support system for demand forecasting DSS_DF is presented. A demand forecast is generated in DSS_DF by combining four forecasts values. Two of them are obtained independently, one by a customer and the other by a market expert. They represent subjective judgments on future demand, given as linguistic values, such as “demand is around a certain value” or “demand is not lower than a certain value”, etc. Two additional forecasts are crisp values, obtained using conventional statistical methods, one using time-series analysis based on decomposition (TSAD), and the other using an auto regressive integrated moving average (ARMA) model. The combination of these four forecast values into one improved forecast is made by applying fuzzy IF-THEN rules. A modified Mamdani-style inference is used, which enables reasoning with fuzzy inputs. A new learning mechanism is developed and incorporated into the DSS_DF to adapt the rule bases that combine the individual forecasted values. The rule bases are adapted taking into consideration the performance of each of the forecast methods recorded in the past. The application of DSS_DF is demonstrated by an illustrative example. The forecasts obtained by DSS_DF are compared with results procured by applying the conventional TSAD and ARMA methods separately. The results obtained are encouraging and indicate that combining forecasts obtained by different methods may be beneficial.
Original languageEnglish
Pages (from-to)1713-1725
JournalFuzzy Sets and Systems
Volume157
Issue number12
DOIs
Publication statusPublished - Mar 2006

Fingerprint

Demand Forecasting
Fuzzy Decision
Time series analysis
Decision Support Systems
Decision support systems
Forecast
Decomposition
Linguistics
Rule Base
Time Series Analysis
Decompose
Learning
Customers
Reasoning
Demand

Bibliographical note

This paper is not available on the repository

Funder

Engineering and Physical Sciences Research Council (EPSRC), grant no.<br/>GR/N11841

Keywords

  • Fuzzy inference systems
  • Forecasting
  • Learning
  • Decision support systems

Cite this

Fuzzy decision support system for demand forecasting with a learning mechanism. / Petrovic, Dobrila; Xie, Ying; Burnham, Keith.

In: Fuzzy Sets and Systems, Vol. 157, No. 12, 03.2006, p. 1713-1725.

Research output: Contribution to journalArticle

Petrovic, Dobrila ; Xie, Ying ; Burnham, Keith. / Fuzzy decision support system for demand forecasting with a learning mechanism. In: Fuzzy Sets and Systems. 2006 ; Vol. 157, No. 12. pp. 1713-1725.
@article{c896a67c278d44e28b9de26f632f120c,
title = "Fuzzy decision support system for demand forecasting with a learning mechanism",
abstract = "In this paper, a new decision support system for demand forecasting DSS_DF is presented. A demand forecast is generated in DSS_DF by combining four forecasts values. Two of them are obtained independently, one by a customer and the other by a market expert. They represent subjective judgments on future demand, given as linguistic values, such as “demand is around a certain value” or “demand is not lower than a certain value”, etc. Two additional forecasts are crisp values, obtained using conventional statistical methods, one using time-series analysis based on decomposition (TSAD), and the other using an auto regressive integrated moving average (ARMA) model. The combination of these four forecast values into one improved forecast is made by applying fuzzy IF-THEN rules. A modified Mamdani-style inference is used, which enables reasoning with fuzzy inputs. A new learning mechanism is developed and incorporated into the DSS_DF to adapt the rule bases that combine the individual forecasted values. The rule bases are adapted taking into consideration the performance of each of the forecast methods recorded in the past. The application of DSS_DF is demonstrated by an illustrative example. The forecasts obtained by DSS_DF are compared with results procured by applying the conventional TSAD and ARMA methods separately. The results obtained are encouraging and indicate that combining forecasts obtained by different methods may be beneficial.",
keywords = "Fuzzy inference systems, Forecasting, Learning, Decision support systems",
author = "Dobrila Petrovic and Ying Xie and Keith Burnham",
note = "This paper is not available on the repository",
year = "2006",
month = "3",
doi = "10.1016/j.fss.2006.03.011",
language = "English",
volume = "157",
pages = "1713--1725",
journal = "Fuzzy Sets and Systems",
issn = "0165-0114",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Fuzzy decision support system for demand forecasting with a learning mechanism

AU - Petrovic, Dobrila

AU - Xie, Ying

AU - Burnham, Keith

N1 - This paper is not available on the repository

PY - 2006/3

Y1 - 2006/3

N2 - In this paper, a new decision support system for demand forecasting DSS_DF is presented. A demand forecast is generated in DSS_DF by combining four forecasts values. Two of them are obtained independently, one by a customer and the other by a market expert. They represent subjective judgments on future demand, given as linguistic values, such as “demand is around a certain value” or “demand is not lower than a certain value”, etc. Two additional forecasts are crisp values, obtained using conventional statistical methods, one using time-series analysis based on decomposition (TSAD), and the other using an auto regressive integrated moving average (ARMA) model. The combination of these four forecast values into one improved forecast is made by applying fuzzy IF-THEN rules. A modified Mamdani-style inference is used, which enables reasoning with fuzzy inputs. A new learning mechanism is developed and incorporated into the DSS_DF to adapt the rule bases that combine the individual forecasted values. The rule bases are adapted taking into consideration the performance of each of the forecast methods recorded in the past. The application of DSS_DF is demonstrated by an illustrative example. The forecasts obtained by DSS_DF are compared with results procured by applying the conventional TSAD and ARMA methods separately. The results obtained are encouraging and indicate that combining forecasts obtained by different methods may be beneficial.

AB - In this paper, a new decision support system for demand forecasting DSS_DF is presented. A demand forecast is generated in DSS_DF by combining four forecasts values. Two of them are obtained independently, one by a customer and the other by a market expert. They represent subjective judgments on future demand, given as linguistic values, such as “demand is around a certain value” or “demand is not lower than a certain value”, etc. Two additional forecasts are crisp values, obtained using conventional statistical methods, one using time-series analysis based on decomposition (TSAD), and the other using an auto regressive integrated moving average (ARMA) model. The combination of these four forecast values into one improved forecast is made by applying fuzzy IF-THEN rules. A modified Mamdani-style inference is used, which enables reasoning with fuzzy inputs. A new learning mechanism is developed and incorporated into the DSS_DF to adapt the rule bases that combine the individual forecasted values. The rule bases are adapted taking into consideration the performance of each of the forecast methods recorded in the past. The application of DSS_DF is demonstrated by an illustrative example. The forecasts obtained by DSS_DF are compared with results procured by applying the conventional TSAD and ARMA methods separately. The results obtained are encouraging and indicate that combining forecasts obtained by different methods may be beneficial.

KW - Fuzzy inference systems

KW - Forecasting

KW - Learning

KW - Decision support systems

U2 - 10.1016/j.fss.2006.03.011

DO - 10.1016/j.fss.2006.03.011

M3 - Article

VL - 157

SP - 1713

EP - 1725

JO - Fuzzy Sets and Systems

JF - Fuzzy Sets and Systems

SN - 0165-0114

IS - 12

ER -