THE ACCURACY OF EXCHANGE RATE FORECASTS IN ROMANIA

Mihaela Simionescu

Journal of Social and Economic Statistics, 2015, vol. 4, issue 1, 54-64

Abstract: The main aim of this research is to predict the average exchange rate RON/USD in Romania using various quantitative methods. Recent researches have confirmed the prediction power of neural networks, but in this article econometric models and exponential smoothing techniques have been employed. For predicting the average RON/USD exchange rate using neural networks the following variables have been used: the real growth of monetary supply M2, the real interest rate, index of production prices and real exchange rate. For predictions based on multiplicative Holt-Winters model on 2011-2013, we obtained a recognised superiority in terms of accuracy, outperforming other predictions based on neural networks (perceptron multilayer and radial basis function) and econometric models (autoregressive model and vector-autoregressive model).

Keywords: exchange rate; forecasts; neural network; econometric model; accuracy (search for similar items in EconPapers)
JEL-codes: C51 C53 (search for similar items in EconPapers)
Date: 2015
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.jses.ase.ro/downloads/Vol4NO1/Simionescu.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aes:jsesro:v:4:y:2015:i:1:p:54-64

Access Statistics for this article

Journal of Social and Economic Statistics is currently edited by Zizi Goschin

More articles in Journal of Social and Economic Statistics from Bucharest University of Economic Studies Contact information at EDIRC.
Bibliographic data for series maintained by Bogdan-Vasile Ileanu ().