probabilistic neural networks (pnns)

Forecasting is one of the effective tools for planning and establishing the financial strategies. Forecasting accuracy is also one of the most important factors in choosing the forecasting method. Nowadays, despite the numerous forecasting models available, accurate forecasting is not yet a simple task, especially in financial markets. Thus, different models have been combined together in order to achieve more accurate results. Combining different models or using hybrid forecasting models is a common way for overcoming deficiecies of the single models and improving their performance. In the literature, several hybrid models of multilayer perceptrons have been proposed in order to overcome the disadvantages of these models. In this paper, a new hybrid model of multilayer perceptrons is proposed using probabilistic neural classifiers. The proposed model improves the performance of the multilayer perceptrons using the unique advantages of the probabilistic neural classifiers in detecting the break points and better and more complete modeling of the specific patterns in the under-study time series. Empirical results of exchange rate forecasting indicate the efficiency of the proposed model in comparison with other models.

Fuzzy autoregressive integrated moving average models are improved versions of the classic autoregressive integrated moving average (ARIMA) models, proposed in order to overcome the data limitation of ARIMA models. In this paper,FARIMA models are combined with probabilistic classifiers in order to yield a more accurate model than FARIMA in financially incomplete data situations. Empirical results of using proposed hybrid model in exchange rate market forecasting indicate that the proposed model exhibits effectively improved forecasting accuracy. Thus, the proposed model can be used as an alternative to exchange rate forecasting tools, especially when the scant data is made available over a short span of time.