Search

In this study, a new hybrid forecasting method is proposed. The proposed method is called autoregressive adaptive network fuzzy inference system (AR–ANFIS). AR–ANFIS can be shown in a network structure. The architecture of the network has two parts. The first part is an ANFIS structure and the second part is a linear AR model structure. In the literature, AR models and ANFIS are widely used in time series forecasting. Linear AR models are used according to model-based strategy. A nonlinear model is employed by using ANFIS. Moreover, ANFIS is a kind of data-based modeling system like artificial neural network. In this study, a linear and nonlinear forecasting model is proposed by creating a hybrid method of AR and ANFIS. The new method has advantages of data-based and model-based approaches. AR–ANFIS is trained by using particle swarm optimization, and fuzzification is done by using fuzzy C-Means method. AR–ANFIS method is examined on some real-life time series data, and it is compared with the other time series forecasting methods. As a consequence of applications, it is shown that the proposed method can produce accurate forecasts. [ABSTRACT FROM AUTHOR]

It had been asserted that the more kind of instruments meant the less risk of portfolio until 1950. Conventional portfolio theory that proposed to invest for instruments was given up after mean- variance model was proposed and modern portfolio theory was established. The mathematical programming techniques are used to solve mean-variance model. In recent years, artificial intelligence methods have been employed for portfolio optimization. In this study, standard and guaranteed convergence particle swarm optimization methods have been applied to optimize the portfolio that contains IMKB 30 stock shares. The results are compared to the other results that are obtained through mathematical programming. [ABSTRACT FROM AUTHOR]

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]

Abstract: In recent years, artificial neural networks have been used for time series forecasting. Determining architecture of artificial neural networks is very important problem in the applications. In this study, the problem in which time series are forecasted by feed forward neural networks is examined. Various model selection criteria have been used for the determining architecture. In addition, a new model selection strategy based on well-known model selection criteria is proposed. Proposed strategy is applied to real and simulated time series. Moreover, a new direction accuracy criterion called modified direction accuracy criterion is discussed. The new model selection strategy is more reliable than known model selection criteria. [Copyright &y& Elsevier]

An introduction is presented in which the editor discusses articles in the issue on topics including ideas to gather case studies and data analysis from the papers presented at the eleventh International Statistics Days Conference (ISDC).

Abstract: In a clustering problem, it would be better to use fuzzy clustering if there was an uncertainty in determining clusters or memberships of some units. Determining the number of cluster has an important role on obtaining sensible and sound results in clustering analysis. In many clustering algorithm, it is firstly need to know number of cluster. However, there is no pre-information about the number of cluster in general. The process of determining the most proper number of cluster is called as cluster validation. In the available fuzzy clustering literature, the most proper number of cluster is determined by utilizing cluster validation indices. When the data contain complexity are being analyzed, cluster validation indices can produce conflictive results. Also, there is no criterion point out the best index. In this study, artificial neural networks are employed to determine the number of cluster. The data is taken as input so the output is membership degree. The proposed method is applied some data and obtained results are compared to those obtained from validation indices like PC, XB, and CE. It is shown that the proposed method produce accurate results. [ABSTRACT FROM AUTHOR]