You are here

Home » Content

ZAMAN SERİSİ ANALİZİNDE MLP YAPAY SİNİR AĞLARI VE ARIMA MODELİNİN KARŞILAŞTIRILMASI

COMPARASION OF MLP ARTIFICAL NEURAL NETWORK AND ARIMA METHOD IN TIME SERIES ANALYSIS

Journal Name:

  • Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi

Publication Year:

  • 2009

Key Words:

Keywords (Original Language):

Author NameUniversity of AuthorFaculty of Author
Abstract (2. Language): 
In this study, Box-Jenkins methods commonly used in time series analysis and Artifical neural network were compared. Monthly and daily echange rates (YTL/$) were used as data set. Different Box-Jenkins and artifical neural network models were created and best performed models were chosen to compare both technics. Results show that artifical neural network is a successful method for forecasting financial data.
Bookmark/Search this post with
Abstract (Original Language): 
Bu çalısmada zaman serisi analizinde yaygın olarak kullanılan Box-Jenkis modelleri ile ileri beslemeli yapay sinir aglarının bir karsılastırması yapılmıstır. Veri seti olarak aylık ve günlük döviz (YTL/$) kuru verileri kullanılmıstır. Farklı Box-Jenkins ve yapay sinir agları modelleri olusturulmus, her bir teknik için en iyi sonuçları veren modeller seçilerek karsılastırma yapılmıstır. Elde edilen sonuçlar Yapay sinir aglarının finansal verilerin tahmininde kullanılabilecek basarılı bir yöntem oldugunu göstermistir.
FULL TEXT (PDF): 
PDF icon arastirmax-zaman-serisi-analizinde-mlp-yapay-sinir-aglari-arima-modelinin-karsilastirilmasi.pdf
  • 1
161-172
  • Turkish

REFERENCES

References: 

FAUSETT, Laurene; (1994), Fundamentals of Neural Networks: Architectures,
Algorithms and Applications, Prentice Hall.
HANN, Tae Horn ve STEURER, Elmar; (1996), “Much Ado About Nothing?
Exchange Rate Forecasting: Neural Networks Vs. Linear Models
Using Monthly And Weekly Data”, Neurocomputing, Vol. 10,
ss.323–339.
KAMRUZZAMMAN, Joarder ve SARKER, Ruhul A.; (2003), “Forecasting of
Currency Exchange Rates using ANN: A Case Study”, Proc. IEEE
International Conference on Neural Networks & Signal
Processing (ICNNSP03), Nanjing, China, ss.793-797.
KUAN, Chung Ming ve LIU, Tung; (1995), “Forecasting Exchange Rates
Using Feedforward And Recurrent Neural Networks”, Journal of
Applied Econometrics, Vol. 10, pp. 347–364.
ÖZTEMEL, Ercan; (2003), Yapay Sinir Agları, Papatya Yayıncılık, stanbul.
TANG, Zaiyong ve FISHWICK, Paul A.; (1993), “Feedforward Neural Nets As
Models For Time Series Forecasting”,ORSA Journal on
Computing, 5(4), ss.374–385.
WEIGEND, Andreas S., HUBERMAN, Barnardo A. ve RUMELHART, David
E.; (1992), “Predicting sunspots and exchange rates with connectionist
Networks In Nonlinear modeling and forecasting”, Addison-Welsey,
ss. 395–432.
WU, Berlin; (1995), “Model-Free Forecasting For Nonlinear Time Series (With
Application to Exchange Rates”, Computational Statistics and Data
Analysis, Vol.19, ss. 433–459.
ZHANG, Gioqinang ve HU, Michael Y. ;(1998), “Neural Network Forecasting
of the British Pound/US Dollar Exchange Rate”, OMEGA: Int.
Journal of Management Science, Vol. 26, ss. 495-506.
ZHANG, Gioqinang, PATUWO, B. Eddy ve HU, Michael Y., (1998)
“Forecasting With Artificial Neural Networks: The State Of The Art”,
International Journal of Forecasting, Vol.14, ss.35-62.

Thank you for copying data from http://www.arastirmax.com