Predicting exchange rates using a novel "cointegration based neuro-fuzzy system"

Behrooz Gharleghi, Abu Hassan Shaari Md Nor, Najla Shafighi

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The present study focuses upon the applications of currently available intelligence techniques to forecast exchange rates in short and long horizons. The predictability of exchange rate returns is investigated through the use of a novel cointegration-based neuro-fuzzy system, which is a combination of a cointegration technique; a Fuzzy Inference System; and Artificial Neural Networks. The Relative Price Monetary Model for exchange rate determination is used to determine the inputs, consisting of macroeconomic variables and the type of interactions amongst the variables, in order to develop the system. Considering exchange rate returns of three ASEAN countries (Malaysia, the Philippines and Singapore), our results reveal that the cointegration-based neuro-fuzzy system model consistently outperforms the Vector Error Correction Model by successfully forecasting exchange rate monthly returns with a high level of accuracy.

Original languageEnglish
Pages (from-to)88-103
Number of pages16
JournalInternational Economics
Volume137
DOIs
Publication statusPublished - May 2014

Fingerprint

Exchange rates
Cointegration
Exchange rate returns
Fuzzy systems
Neuro-fuzzy
System model
Exchange rate determination
Artificial neural network
Vector error correction model
Macroeconomic variables
Predictability
Singapore
Inference
Relative prices
Malaysia
Interaction
Philippines

Keywords

  • Error correction model
  • Exchange rate
  • Intelligence systems
  • Neural networks
  • Unit root

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Economics, Econometrics and Finance(all)

Cite this

Predicting exchange rates using a novel "cointegration based neuro-fuzzy system". / Gharleghi, Behrooz; Md Nor, Abu Hassan Shaari; Shafighi, Najla.

In: International Economics, Vol. 137, 05.2014, p. 88-103.

Research output: Contribution to journalArticle

@article{d1042ed09d9f48459e2c4e440df4c4dd,
title = "Predicting exchange rates using a novel {"}cointegration based neuro-fuzzy system{"}",
abstract = "The present study focuses upon the applications of currently available intelligence techniques to forecast exchange rates in short and long horizons. The predictability of exchange rate returns is investigated through the use of a novel cointegration-based neuro-fuzzy system, which is a combination of a cointegration technique; a Fuzzy Inference System; and Artificial Neural Networks. The Relative Price Monetary Model for exchange rate determination is used to determine the inputs, consisting of macroeconomic variables and the type of interactions amongst the variables, in order to develop the system. Considering exchange rate returns of three ASEAN countries (Malaysia, the Philippines and Singapore), our results reveal that the cointegration-based neuro-fuzzy system model consistently outperforms the Vector Error Correction Model by successfully forecasting exchange rate monthly returns with a high level of accuracy.",
keywords = "Error correction model, Exchange rate, Intelligence systems, Neural networks, Unit root",
author = "Behrooz Gharleghi and {Md Nor}, {Abu Hassan Shaari} and Najla Shafighi",
year = "2014",
month = "5",
doi = "10.1016/j.inteco.2013.12.001",
language = "English",
volume = "137",
pages = "88--103",
journal = "International Economics",
issn = "2110-7017",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Predicting exchange rates using a novel "cointegration based neuro-fuzzy system"

AU - Gharleghi, Behrooz

AU - Md Nor, Abu Hassan Shaari

AU - Shafighi, Najla

PY - 2014/5

Y1 - 2014/5

N2 - The present study focuses upon the applications of currently available intelligence techniques to forecast exchange rates in short and long horizons. The predictability of exchange rate returns is investigated through the use of a novel cointegration-based neuro-fuzzy system, which is a combination of a cointegration technique; a Fuzzy Inference System; and Artificial Neural Networks. The Relative Price Monetary Model for exchange rate determination is used to determine the inputs, consisting of macroeconomic variables and the type of interactions amongst the variables, in order to develop the system. Considering exchange rate returns of three ASEAN countries (Malaysia, the Philippines and Singapore), our results reveal that the cointegration-based neuro-fuzzy system model consistently outperforms the Vector Error Correction Model by successfully forecasting exchange rate monthly returns with a high level of accuracy.

AB - The present study focuses upon the applications of currently available intelligence techniques to forecast exchange rates in short and long horizons. The predictability of exchange rate returns is investigated through the use of a novel cointegration-based neuro-fuzzy system, which is a combination of a cointegration technique; a Fuzzy Inference System; and Artificial Neural Networks. The Relative Price Monetary Model for exchange rate determination is used to determine the inputs, consisting of macroeconomic variables and the type of interactions amongst the variables, in order to develop the system. Considering exchange rate returns of three ASEAN countries (Malaysia, the Philippines and Singapore), our results reveal that the cointegration-based neuro-fuzzy system model consistently outperforms the Vector Error Correction Model by successfully forecasting exchange rate monthly returns with a high level of accuracy.

KW - Error correction model

KW - Exchange rate

KW - Intelligence systems

KW - Neural networks

KW - Unit root

UR - http://www.scopus.com/inward/record.url?scp=84892455569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892455569&partnerID=8YFLogxK

U2 - 10.1016/j.inteco.2013.12.001

DO - 10.1016/j.inteco.2013.12.001

M3 - Article

VL - 137

SP - 88

EP - 103

JO - International Economics

JF - International Economics

SN - 2110-7017

ER -