TIME SERIES FORECASTING USING NEURAL NETWORKS

Journal Title: Challenges of the Knowledge Society - Year 2013, Vol 3, Issue 0

Abstract

Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.

Authors and Affiliations

BOGDAN OANCEA, ŞTEFAN CRISTIAN CIUCU

Keywords

Related Articles

HOBBES’ POLITICAL PHILOSOPHY

This is basically an attempt at an original conceptual reconstruction of Hobbes’ philosophy as set in Lehiathan, namely one in the view of which Hobbes was neither an atheist nor an absolutist, as the standard interpreta...

GENERAL CONSIDERATION REGARDING EU LAW IN THE DOMAIN OF CULTURAL HERITAGE

The cultural heritage is a rich and diverse mosaic of cultural and creative expressions, our inheritance from previous generations of people and our legacy for those to come. In the terms of the Convention concerning the...

SKEWNESS IN STOCK RETURNS: EVIDENCE FROM THE BUCHAREST STOCK EXCHANGE DURING 2000 – 2011

Our paper investigates the symmetry in stock returns of the 30 most liquid companies traded on Bucharest Stock Exchange during 2000 – 2011 and also the most representative 5 market indices. Our daily data shows that skew...

LEGAL CONSEQUENCES OF MERGERS AND ACQUISITIONS

The research analyses the legal effects of mergers and acquisitions from the Romanian Company Law perspective, underlining certain general principles, the procedure of annulment of such a legal transformation of companie...

EVOLUTION OF THE PHENOMENON INTEGRATION IN LATIN AMERICA (SOUTH AMERICA)

With the end of the Cold War, the creation of a South American economic space has become an important priority of regional powers (Brazil, Argentina, Chile), and the great powers after the war, the U.S. and the European...

Download PDF file
  • EP ID EP104929
  • DOI -
  • Views 104
  • Downloads 0

How To Cite

BOGDAN OANCEA, ŞTEFAN CRISTIAN CIUCU (2013). TIME SERIES FORECASTING USING NEURAL NETWORKS. Challenges of the Knowledge Society, 3(0), 1402-1408. https://europub.co.uk/articles/-A-104929