Search

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. [ABSTRACT FROM AUTHOR]

The observations of some real time series such as temperature and stock market can take different values in a day. Instead of representing the observations of these time series by real numbers, employing linguistic values or fuzzy sets can be more appropriate. In recent years, many approaches have been introduced to analyze time series consisting of observations which are fuzzy sets and such time series are called fuzzy time series. In this study, a novel approach is proposed to analyze high order fuzzy time series model. The proposed method is applied to IMKB data and the obtained results are discussed. IMKB data is also analyzed by using some other fuzzy time series methods available in the literature and obtained results are compared to results obtained from the proposed method. As a result of the comparison, it is seen that the proposed method produce accurate forecasts. [ABSTRACT FROM AUTHOR]