Author/Authors :
alpaslan, faruk ondokuz mayis üniversitesi, kurupelit kampüsü - fen edebiyat fakültesi - istatistik bölümü, Turkey , egrioglu, erol ondokuz mayis üniversitesi, kurupelit kampüsü - fen edebiyat fakültesi - istatistik bölümü, Turkey , aladag, çagdas hakan hacettepe üniversitesi - fen fakültesi - istatistik bölümü, Turkey , ilter, damla ondokuz mayis üniversitesi, kurupelit kampüsü - fen edebiyat fakültesi - istatistik bölümü, Turkey , dalar, ali zafer giresun üniversitesi, gazipasa yerleskesi - fen edebiyat fakültesi - istatistik bölümü, Turkey
Abstract :
In the literature, artificial neural networks have been frequently used for the problem of time series forecasting. There are many types of artificial neural networks in prediction of time series. Single multiplicative neuron model is firstly proposed in literature by Yadav et al. (2007). Single multiplicative neuron model uses single multiplicative aggregation function unlike the other artificial neuron models. Single neuron which uses single multiplicative neuron model was shown that in Yadav et al. (2007) successful results were obtained in time series forecasting problem of artificial neural network by using well-known time series in literature. It has known that single neuron and feed forward neural networks based on single multiplicative neuron model obtained quite successful results in time series prediction. In this study, Istanbul gold exchange and Index 100 for the stocks and bonds exchange market of Istanbul time series are analyzed by using single multiplicative neuron model artificial neural networks. In analyze, artificial bee colony algorithm and back propagation algorithm methods are used for the training of single multiplicative neuron, and obtained results are compared.
NaturalLanguageKeyword :
Artificial bee colony , Back propagation algorithm , Forecasting , Single multiplicative neuron model , Training algorithm