On A Model For Predicting The Exchange Rate Euro-Leu With A Nar Neural Network
Dumitru Ciobanu · 2012
Developing new methods for predictive modeling of time series and application of existing techniques in many other areas will be a permanent concern for both researchers and companies that are interested to gain competitive advantages. In this paper, I used Matlab software suite to create a NAR (nonlinear autoregressive) neural network able to predict the following values of the series of exchange rate euro-leu. Using graphs obtained from numerous simulations emphasize the chaotic nature of the series. I also explore the possibility of improving the predictions with a time series made of arithmetic averages of predictions.