Foreign exchange rate forecasting by artificial neural networks

2011

The present statistical models used for forecasting cannot effectively handle uncertainty and instability nature of foreign exchange data. In this work, an artificial neural network foreign exchange rate forecasting model (AFERFM) was designed for foreign exchange rate forecasting to correct some of these problems. The design was divided into two phases, namely: training and forecasting. In the training phase, back propagation algorithm was used to train the foreign exchange rates and learn how to approximate input. Sigmoid Activation Function (SAF) was used to transform the input into a standard range [0, 1]. The learning weights were randomly assigned in the range [-0.1, 0.1] to obtain the output consistent with the training. SAF was depicted using a hyperbolic tangent in order to increase the learning rate and make learning efficient. Feed forward Network was used to improve the efficiency of the back propagation. Multilayer Perceptron Network was designed for forecasting. The da...

Intelligent Decision Technologies, 2018

Financial time series data is very chaotic, noisy, fluctuating and nonlinear as different events have occurred in various time periods. Therefore, it is very challenging for researchers to develop the accurate predictive model. Prediction for Foreign Exchange rate is also a very crucial task for N days ahead prediction because of volatile nature of Foreign Exchange rate data. It is also become highly desirable due to it's role in financial and managerial decision making capacity of any country. A lot of efforts have been done by researchers over many years for the development of efficient models to improve the forecasting accuracy. As a result, various important time series forecasting models have been evolved in literature. From the literature survey we have analyzed that statistical techniques are not able to efficiently predict the Foreign Exchange rate. Hence, different machine learning techniques have been used by many researchers for accurate prediction. Over the years different types of neural network models such as multi-layer perceptron, radial basis function neural network, functional link artificial neural network and integrated model such as auto-regressive integrated moving average models are developed to predict the currency exchange rates of different countries with varying parameters. In this paper, we divide our effort into two parts. In the first part, we have reviewed a few selected models based on neural networks and statistical methods including fundamental and technical aspects of currency exchange rate prediction. In the second part, we have made a thorough and careful empirical study of the models reviewed in part one. Our study reveals that the daily currency exchange rates with multi-layer neural network having Bayesian learning technique produces more accurate results against the multi-layer neural network with back propagation learning technique. Similarly, integrated models of radial basis function neural network and functional link neural networks produce less amount of error in comparison to single radial basis neural networks and functional link neural network models. Additionally, we critically analyze an integrated work on statistical model such as auto-regressive integrated moving average model with neural networks and revealed that the integrated models produces better results than the individual models.

Exchange rates play an important role in controlling dynamics of the foreign exchange market. Predicting exchange rates has become one of the most challenging applications of financial time series forecasting due to its unpredictability and volatility. This research study is to develop and compare the accuracy of two models; Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH) as the time series model and Feedforward neural network with the Backpropagation algorithm as the Artificial Neural Network (ANN) model for predicting daily currency exchange rate of US Dollar against Sri Lankan Rupee (USD/LKR). For both models, past lagged observations of the data series and moving average technical indicators were employed as the explanatory variables and the predictive performance were evaluated using a number of widely used statistical metric. According to the performance of two models, it can be concluded that the ANN based model performs better when compared with the GARCH ...

International Journal of Academic Research in Accounting, Finance and Management Sciences, 2014

Forecasting of financial data has been a field of research since the efficiency of prediction is essential for strategical decision making. Forecasting exchange rates is not a simple task because it is influenced by many factors and linear models are not able to capture nonlinear relationships in the data. Therefore ANNs have been used in financial forecasting problems since it is capable of handling complex data. The aim of this study is to consider predictive accuracy of ANNs with normalized back propagation using the historical Euro and Turkish Lira (EUR/TRY) exchange rates. The data is obtained from CBRT (Central Bank of the Republic of Turkey) over the period 2010-2013. Several factors affect the accuracy of neural network in the implementation process. Various structures are built by changing the number of neurons, transfer functions and learning algorithms to acquire higher performance. This empirical research has been a comparative study of accuracy in different ANN architectures also in different time horizons. The results are evaluated by MSE (Mean Squared Error) values of each case and it has been found out that ANNs can closely forecast the future EUR/TRY exchange rates.

International Journal of Engineering & Technology

Forecasting exchange rate has always been in demand as it is very important for the international traders to predict how their money will perform against other currencies. So different methods have been applied by the researchers to accurately predict the exchange rates so that it can assist in taking decision while trading. From all the models the Artificial Neural Network (ANN) has given consistent performance in prediction by overcoming the limitations of other models and has outperformed all the models in terms of efficiency. The evolution of ANN is remarkable. In this paper, we have given the performance of different network models used by researchers to predict the exchange rates of major currencies in the future.

REVISTA ECONOMICA – Journal of Economic-Financial Theory and Practice, 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.

Omega, 1998

Neural networks have successfully been used for exchange rate forecasting. However, due to a large number of parameters to be estimated empirically, it is not a simple task to select the appropriate neural network architecture for an exchange rate forecasting problem. Researchers often overlook the eect of neural network parameters on the performance of neural network forecasting. This paper examines the eects of the number of input and hidden nodes as well as the size of the training sample on the in-sample and out-of-sample performance. The British pound/US dollar is used for detailed examinations. It is found that neural networks outperform linear models, particularly when the forecast horizon is short. In addition, the number of input nodes has a greater impact on performance than the number of hidden nodes, while a larger number of observations do reduce forecast errors.

Neurocomputing, 2000

This paper reports empirical evidence that a neural network model is applicable to the prediction of foreign exchange rates. Time series data and technical indicators, such as moving average, are fed to neural networks to capture the underlying`rulesa of the movement in currency exchange rates. The exchange rates between American Dollar and "ve other major currencies, Japanese Yen, Deutsch Mark, British Pound, Swiss Franc and Australian Dollar are forecast by the trained neural networks. The traditional rescaled range analysis is used to test the`e$ciencya of each market before using historical data to train the neural networks. The results presented here show that without the use of extensive market data or knowledge, useful prediction can be made and signi"cant paper pro"ts can be achieved for out-of-sample data with simple technical indicators. A further research on exchange rates between Swiss Franc and American Dollar is also conducted. However, the experiments show that with e$cient market it is not easy to make pro"ts using technical indicators or time series input neural networks. This article also discusses several issues on the frequency of sampling, choice of network architecture, forecasting periods, and measures for evaluating the model's predictive power. After presenting the experimental results, a discussion on future research concludes the paper.

Exchange rate forecasting has become a new research topic in present time for best market strategy, planning of investment for investor in foreign project and also for business profit. The methods or process which give the accurate forecasting result are not easy because there are several types of forecasting methods. Exchange Rate Forecasting is most important financial topic for individual investor, stock fund manager, financial analyst for their investment and stock market. Forecasting is to predict the future value of a particular field with the help of previous value or history. Various types of forecasting can be possible like exchange rate forecasting, stock market forecasting, gold price forecasting which affects the economy of a country. Now, there is a drastic change in Indian Rupee(INR) in terms of United State Dollar(USD) from 2009 to 2014. In exchange rate forecasting, there are various type of performance parameter on the basic of error by which we can consider which method gives the best forecasting result. These are mean square error, mean absolute error, root mean square error etc. Error can be calculate as the difference between the actual value and forecasted value. Neural Network gives the better result than time series method. Adaptive Neuro-Fuzzy Inference System is better than Time Series Method and Neural Network. Many factor affects the Indian Rupee which are Economic Activities, Interest Rate, Stock, Money Supply, In neural network, total data set can be divided into training and testing data and then train the dataset. According to the training, error can be calculated and compare with time series.

This paper describes the analysis of a neural network used to predict currency exchange rates in comparison to technical analysis. The neural network structures used are a multilayer perceptron and a Volterra network.