A new genetic fuzzy system approach for parameter estimation of ARIMA model

Saima Hassan*, Jafreezal Jaafar, Brahim S. Belhaouari, Abbas Khosravi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

The Autoregressive Integrated moving Average model is the most powerful and practical time series model for forecasting. Parameter estimation is the most crucial part in ARIMA modeling. Inaccurate and wrong estimated parameters lead to bias and unacceptable forecasting results. Parameter optimization can be adopted in order to increase the demand forecasting accuracy. A paradigm of the fuzzy system and a genetic algorithm is proposed in this paper as a parameter estimation approach for ARIMA. The new approach will optimize the parameters by tuning the fuzzy membership functions with a genetic algorithm. The proposed Hybrid model of ARIMA and the genetic fuzzy system will yield acceptable forecasting results.

Original languageEnglish
Title of host publicationInternational Conference on Fundamental and Applied Sciences 2012, ICFAS 2012
Pages455-459
Number of pages5
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2nd International Conference on Fundamental and Applied Sciences 2012, ICFAS 2012 - Kuala Lumpur, Malaysia
Duration: 12 Jun 201214 Jun 2012

Publication series

NameAIP Conference Proceedings
Volume1482
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference2nd International Conference on Fundamental and Applied Sciences 2012, ICFAS 2012
Country/TerritoryMalaysia
CityKuala Lumpur
Period12/06/1214/06/12

Keywords

  • ARIMA
  • Genetic fuzzy system
  • forecasting
  • hybrid model
  • parameter estimation

Fingerprint

Dive into the research topics of 'A new genetic fuzzy system approach for parameter estimation of ARIMA model'. Together they form a unique fingerprint.

Cite this