A COMPARISON BETWEEN THREE PREDICTIVE MODELS OF COMPUTATIONAL INTELLIGENCE

Dumitru Ciobanu and Bar Mary Violeta
Additional contact information
Dumitru Ciobanu: University of Craiova
Bar Mary Violeta: University of Craiova

Annals - Economy Series, 2013, vol. 6, 62-74

Abstract: Time series prediction is an open problem and many researchers are trying to find new predictive methods and improvements for the existing ones. Lately methods based on neural networks are used extensively for time series prediction. Also, support vector machines have solved some of the problems faced by neural networks and they began to be widely used for time series prediction. The main drawback of those two methods is that they are global models and in the case of a chaotic time series it is unlikely to find such model. In this paper it is presented a comparison between three predictive from computational intelligence field one based on neural networks one based on support vector machine and another based on chaos theory. We show that the model based on chaos theory is an alternative to the other two methods. Keywords: time series prediction, neural networks, support vector machines, chaos theory, exchange rate.

Date: 2013
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.utgjiu.ro/revista/ec/pdf/2013-06/10_Ciobanu,Bar.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:cbu:jrnlec:y:2013:v:6:p:62-74

Access Statistics for this article

More articles in Annals - Economy Series from Constantin Brancusi University, Faculty of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Ecobici Nicolae ( this e-mail address is bad, please contact ).