Evaluation of Artificial Neural Networks in Foreign Exchange Forecasting
Akintunde Mutairu Oyewale
Issue:
Volume 2, Issue 4, July 2013
Pages:
94-101
Received:
17 June 2013
Published:
10 July 2013
Abstract: This study investigates the modeling, description and forecasting of exchange rates of four countries (Great Britain Pound, Japanese Yen, Nigerian Naira and Batswana Pula) using Artificial Neural Network, the objective of this paper is to use ANN to predict the trend of these four currencies. ANN was used in training and learning processes and thereafter the forecast performance was evaluated or measured making use of various loss functions such as root mean square error (RMSE), mean absolute error (MAE), mean absolute error (MAE), mean absolute precision error (MAPE) and Theill inequality coefficient (TIC). The loss functions used are good indicator of measuring the forecast performance of these series, the series with the lowest function gave a best forecast performance. Results show that the ANN is a very effective tool for exchange rate forecasting. Classical statistical methods are unable to efficiently handle the prediction of financial time series due to non-linearity, non-stationarity and high degree of noise. Advanced intelligence techniques have been used in many financial markets to forecast future development of different capital markets. Artificial neural network is a well tested method for financial markets analysis.
Abstract: This study investigates the modeling, description and forecasting of exchange rates of four countries (Great Britain Pound, Japanese Yen, Nigerian Naira and Batswana Pula) using Artificial Neural Network, the objective of this paper is to use ANN to predict the trend of these four currencies. ANN was used in training and learning processes and ther...
Show More
A Method for Topographical Estimation of Lake Bottoms by B-Spline Surface
Issue:
Volume 2, Issue 4, July 2013
Pages:
102-109
Received:
15 July 2013
Published:
10 August 2013
Abstract: The application of B-spline (Basis spline) surface to the estimation of the lake bottom topography is described.By using the analysis of a bivariate B-spline, the shape of the lake bottom is approximated.According to the validity of the estimation by the bivariate B-spline function the method is applied to the actual data of the lake depth.Surveys over the water area have more difficulties than those on land, and the measurement data are distributed quite irregularly. The locations of the measured data donot exist regularly over the lake.Those locations were distributed along with the wake of the boat on which the sample data were collected. The density of the data is quite high in some small regions and quite low in other wide regions.Based on such irregular data, we tried a statistical estimation.The regularized term with a penalty coefficient makesa proper approximation of the parameters of the B-spline functions. There are many factors, such that the number of knots, the locations of those knots, the number of B-spline functions and the coefficient of penalized term.Appropriate information criterion which has sufficient accuracy and a small amount of computation is applied for determination of the optimal model.
Abstract: The application of B-spline (Basis spline) surface to the estimation of the lake bottom topography is described.By using the analysis of a bivariate B-spline, the shape of the lake bottom is approximated.According to the validity of the estimation by the bivariate B-spline function the method is applied to the actual data of the lake depth.Surveys ...
Show More
