Time series modeling and forecasting using memetic algorithms for regime-switching models

Christoph Bergmeir, Isaac Triguero, Daniel Molina, José Luis Aznarte, José Manuel Benitez

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this brief, we present a novel model fitting procedure for the neuro-coefficient smooth transition autoregressive model (NCSTAR), as presented by Medeiros and Veiga. The model is endowed with a statistically founded iterative building procedure and can be interpreted in terms of fuzzy rule-based systems. The interpretability of the generated models and a mathematically sound building procedure are two very important properties of forecasting models. The model fitting procedure employed by the original NCSTAR is a combination of initial parameter estimation by a grid search procedure with a traditional local search algorithm. We propose a different fitting procedure, using a memetic algorithm, in order to obtain more accurate models. An empirical evaluation of the method is performed, applying it to various real-world time series originating from three forecasting competitions. The results indicate that we can significantly enhance the accuracy of the models, making them competitive to models commonly used in the field.

Original languageEnglish
Article number6323088
Pages (from-to)1841-1847
Number of pages7
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume23
Issue number11
DOIs
Publication statusPublished - 2012
Externally publishedYes

Keywords

  • Autoregression
  • memetic algorithms
  • neuro-coefficient smooth transition autoregressive model (NCSTAR)
  • regime-switching models
  • threshold autoregressive model (TAR)

Cite this

Bergmeir, Christoph ; Triguero, Isaac ; Molina, Daniel ; Aznarte, José Luis ; Benitez, José Manuel. / Time series modeling and forecasting using memetic algorithms for regime-switching models. In: IEEE Transactions on Neural Networks and Learning Systems. 2012 ; Vol. 23, No. 11. pp. 1841-1847.
@article{a2103e41c4a54c26ba72ef5b2c856085,
title = "Time series modeling and forecasting using memetic algorithms for regime-switching models",
abstract = "In this brief, we present a novel model fitting procedure for the neuro-coefficient smooth transition autoregressive model (NCSTAR), as presented by Medeiros and Veiga. The model is endowed with a statistically founded iterative building procedure and can be interpreted in terms of fuzzy rule-based systems. The interpretability of the generated models and a mathematically sound building procedure are two very important properties of forecasting models. The model fitting procedure employed by the original NCSTAR is a combination of initial parameter estimation by a grid search procedure with a traditional local search algorithm. We propose a different fitting procedure, using a memetic algorithm, in order to obtain more accurate models. An empirical evaluation of the method is performed, applying it to various real-world time series originating from three forecasting competitions. The results indicate that we can significantly enhance the accuracy of the models, making them competitive to models commonly used in the field.",
keywords = "Autoregression, memetic algorithms, neuro-coefficient smooth transition autoregressive model (NCSTAR), regime-switching models, threshold autoregressive model (TAR)",
author = "Christoph Bergmeir and Isaac Triguero and Daniel Molina and Aznarte, {Jos{\'e} Luis} and Benitez, {Jos{\'e} Manuel}",
year = "2012",
doi = "10.1109/TNNLS.2012.2216898",
language = "English",
volume = "23",
pages = "1841--1847",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
number = "11",

}

Time series modeling and forecasting using memetic algorithms for regime-switching models. / Bergmeir, Christoph; Triguero, Isaac; Molina, Daniel; Aznarte, José Luis; Benitez, José Manuel.

In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 23, No. 11, 6323088, 2012, p. 1841-1847.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Time series modeling and forecasting using memetic algorithms for regime-switching models

AU - Bergmeir, Christoph

AU - Triguero, Isaac

AU - Molina, Daniel

AU - Aznarte, José Luis

AU - Benitez, José Manuel

PY - 2012

Y1 - 2012

N2 - In this brief, we present a novel model fitting procedure for the neuro-coefficient smooth transition autoregressive model (NCSTAR), as presented by Medeiros and Veiga. The model is endowed with a statistically founded iterative building procedure and can be interpreted in terms of fuzzy rule-based systems. The interpretability of the generated models and a mathematically sound building procedure are two very important properties of forecasting models. The model fitting procedure employed by the original NCSTAR is a combination of initial parameter estimation by a grid search procedure with a traditional local search algorithm. We propose a different fitting procedure, using a memetic algorithm, in order to obtain more accurate models. An empirical evaluation of the method is performed, applying it to various real-world time series originating from three forecasting competitions. The results indicate that we can significantly enhance the accuracy of the models, making them competitive to models commonly used in the field.

AB - In this brief, we present a novel model fitting procedure for the neuro-coefficient smooth transition autoregressive model (NCSTAR), as presented by Medeiros and Veiga. The model is endowed with a statistically founded iterative building procedure and can be interpreted in terms of fuzzy rule-based systems. The interpretability of the generated models and a mathematically sound building procedure are two very important properties of forecasting models. The model fitting procedure employed by the original NCSTAR is a combination of initial parameter estimation by a grid search procedure with a traditional local search algorithm. We propose a different fitting procedure, using a memetic algorithm, in order to obtain more accurate models. An empirical evaluation of the method is performed, applying it to various real-world time series originating from three forecasting competitions. The results indicate that we can significantly enhance the accuracy of the models, making them competitive to models commonly used in the field.

KW - Autoregression

KW - memetic algorithms

KW - neuro-coefficient smooth transition autoregressive model (NCSTAR)

KW - regime-switching models

KW - threshold autoregressive model (TAR)

UR - http://www.scopus.com/inward/record.url?scp=84875874320&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2012.2216898

DO - 10.1109/TNNLS.2012.2216898

M3 - Article

VL - 23

SP - 1841

EP - 1847

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 11

M1 - 6323088

ER -