A Comparison between Neural Networks and GARCH Models in Exchange Rate Forecasting

Abstract

Modeling and forecasting of dynamics nominal exchange rate has long been a focus of financial and economic research. Artificial Intelligence (IA) modeling has recently attracted much attention as a new technique in economic and financial forecasting. This paper proposes an alternative approach based on artificial neural network (ANN) to predict the daily exchange rates. Our empirical study is based on a series of daily data in Tunisia. In order to evaluate this approach, we compare it with a generalized autoregressive conditional heteroskedasticity (GARCH) model in terms of their performance. Results indicate that the proposed nonlinear autoregressive (NAR) model is an accurate and a quick prediction method. This finding helps businesses and policymakers to plan more appropriately.

Authors and Affiliations

Fahima Charef, Fethi Ayachi

Keywords

Related Articles

A Research on Determining the Education Level of Seasonal Ornamental Plant Growers and Marketing Methods in Kocaeli

The main purpose of this study is to examine the education level of growers working in Kocaeli – a city located in the Marmara region where ornamental plants are grown densely – and to find out if they received any vocat...

Validity and Reliability of Locomotor Development Inventory in Malaysian Education Context

The purpose of this article is to report the, validity and reliability of locomotor development inventory that has been used to evaluate locomotor development of children aged 7, 8 and 9 years old. The first phase of the...

A Measurement Model of Leadership Communication of Coastal Village Leaders in Terengganu, Malaysia

Leadership communication skill was identified as a significant predictor for an effective organisation. Despite that, lot of leaders especially in village organisation was not getting clear picture for needed skills to p...

Government Expenditure and Economic Growth in Nigeria: An Analysis with Dynamic Ordinary Least Squares

This study investigates the impact of government expenditure on economic growth from 1981 to 2015 using Dynamic Ordinary Least Squares that incorporates endogenity in its estimation. The unit root test using Augmented Di...

Electronic Cigarettes as a Smoking Cessation or as a Gateway to Start Smoking?

Nowadays, the use of electronic cigarettes are increasingly popular among teens and adults. Electronic cigarettes use battery power to operate. Electronic cigarettes function is very similar to a conventional cigarette,...

Download PDF file
  • EP ID EP183698
  • DOI 10.6007/IJARBSS/v6-i1/1993
  • Views 149
  • Downloads 0

How To Cite

Fahima Charef, Fethi Ayachi (2016). A Comparison between Neural Networks and GARCH Models in Exchange Rate Forecasting. International Journal of Academic Research in Business and Social Sciences, 6(1), 265-280. https://europub.co.uk/articles/-A-183698