This book focuses on forecasting foreign exchange rates via artificial neural networks (ANNs), creating and applying the highly useful computational techniques of Artificial Neural Networks (ANNs) to foreign-exchange rate forecasting. The result is an up-to-date review of the most recent research developments in forecasting foreign exchange rates coupled with a highly useful methodological approach to predicting rate changes in foreign currency exchanges.
The book focuses on forecasting foreign exchange rates via artificial neural networks. It creates and applies the highly useful computational techniques of Artificial Neural Networks (ANNs) to foreign-exchange-rate forecasting. The result is an up-to-date review of the most recent research developments in forecasting foreign exchange rates coupled with a highly useful methodological approach to predicting rate changes in foreign currency exchanges. Foreign Exchange Rate Forecasting with Artificial Neural Networks is targeted at both the academic and practitioner audiences. Managers, analysts and technical practitioners in financial institutions across the world will have considerable interest in the book, and scholars and graduate students studying financial markets and business forecast will also have considerable interest in the book. The book discusses the most important advances in foreign-exchange-rate forecasting and then systematically develops a number of new, innovative, and creatively crafted neural network models that reduce the volatility and speculative risk in the forecasting of foreign exchange rates. The book discusses and illustrates three general types of ANN models. Each of these model types reflect the following innovative and effective characteristics: (1) The first model type is a three-layer, feed-forward neural network with instantaneous learning rates and adaptive momentum factors that produce learning algorithms (both online and offline algorithms) to predict foreign exchange rates. (2) The second model type is the three innovative hybrid learning algorithms that have been created by combining ANNs with exponential smoothing, generalized linear auto-regression, and genetic algorithms. Each of these three hybrid algorithms has been crafted to forecast various aspects synergetic performance. (3) The third model type is the three innovative ensemble learning algorithms that combining multiple neural networks into an ensemble output. Empirical results reveal that these creative models can produce better performance with high accuracy or high efficiency.
The purpose of this research is to investigate the forecasting performance of Artificial Neural Network models applied to foreign exchange rates. The study concentrates on the behavior of forecasts of exchange rates generated from the radial basis function (RBF) network models where little previous work exists. Exchange rates examined are the German mark/US dollar, Japanese yen/US dollar, and Italian lira/US dollar. One-step-ahead forecasts from univariate and multivariate RBF models are compared with those generated from ARIMA models, random walk forecasts and the forward rates. Interest rates and the money supply (MI) are used as explanatory variables in the multivariate analyses. Out-of-sample evaluation criteria include root mean squared error, "correct direction", and "speculative direction."
"This thesis deals with three problems, mainly, whether or not data transformations enhance artificial neural network forecasting, as well as choosing the most appropriate loss functions and the ability of artificial neural networks to learn patterns in data. The data used is foreign exchange rates. It is impractical to guage loss functions with yet another loss function, thus, simple characteristics of the functions were isolated and examined for use in the given task. The results showed that while some functions are well suited to the problem of time series prediction, other can produce a less accurate fit subjective to the forecast problem. Previous work has shown time and time again that artificaial neural networks can produce superior results in comparison to other methods, however, an experiment was designed and conducted to determine if the neural networks were actually learning the patterns in the data rather that just producing a better fit. The results were mixed, showing that some exchange rates could beeasily learned while other could not. Finally, 20 different data transformations were compared to forecasting without preprocessing. The results found that 40% of the transformations improved the forecast. The basic and relative differencing functions, as well as one based on regression, were consistent across the time series used and were a statistically significant improvement." (ABSTRACT p. iv)
Forecasting exchange rates is a variable that preoccupies economists, businesses and governments, being more critical to more people than any other variable. In Exchange Rate Forecasting the author sets out to provide a concise survey of the techniques of forecasting - bringing together the various forecasting methods and applying them to the exchange rate in a highly accessible and readable manner. Highly practical in approach, the book provides an understanding of the techniques of forecasting with an emphasis on its applications and use in business decision-making, such as hedging, speculation, investment, financing and capital budgeting. In addition, the author also considers recent developments in the field, notably neural networks and chaos, again, with easy-to-understand explanations of these "rocket science" areas. The practical approach to forecasting is also reflected in the number of examples that pepper the text, whilst descriptions of some of the software packages that are used in practice to generate forecasts are also provided.
Forecasting is one of the most important activities that form the basis for strategic, tactical, and operational decisions in all business organizations. Recently, neural networks have emerged as an important tool for business forecasting. There are considerable interests and applications in forecasting using neural networks. This book provides for researchers and practitioners some recent advances in applying neural networks to business forecasting. A number of case studies demonstrating the innovative or successful applications of neural networks to many areas of business as well as methods to improve neural network forecasting performance are presented.
"This book is the first book to provide opportunities for millions working in economics, accounting, finance and other business areas education on HONNs, the ease of their usage, and directions on how to obtain more accurate application results. It provides significant, informative advancements in the subject and introduces the HONN group models and adaptive HONNs"--Provided by publisher.
This book explores the intuitive appeal of neural networks and the genetic algorithm in finance. It demonstrates how neural networks used in combination with evolutionary computation outperform classical econometric methods for accuracy in forecasting, classification and dimensionality reduction. McNelis utilizes a variety of examples, from forecasting automobile production and corporate bond spread, to inflation and deflation processes in Hong Kong and Japan, to credit card default in Germany to bank failures in Texas, to cap-floor volatilities in New York and Hong Kong. * Offers a balanced, critical review of the neural network methods and genetic algorithms used in finance * Includes numerous examples and applications * Numerical illustrations use MATLAB code and the book is accompanied by a website
