Article

Forecasting foreign exchange rates with artificial neural networks: A review

Institute of Systems Science, Academy of Mathematics and Systems Sciences, School of Knowledge Science, Chinese Academy of Sciences, 100080, Beijing, People's Republic of China; Japan Advanced Institute of Science and Technology, 923-1292, Asahidai, Ishikawa, Japan; Department of Management Sciences, City University of Hong Kong Tat Chee Avenue, Kowloon, Hong Kong; School of Knowledge Science, Japan Advanced Institute of Science and Technology, 923-1292, Asahidai, Ishikawa, Japan; Institute of Systems Science, Academy of Mathematics and Systems Sciences, Chinese Academy of Sciences, 100080, Beijing, People's Republic of China
International Journal of Information Technology and Decision Making (Impact Factor: 1.31). 01/2004; 2(3):145-165. DOI: 10.1142/S0219622004000969

ABSTRACT Forecasting exchange rates is an important financial problem that is receiving increas-ing attention especially because of its difficulty and practical applications. Artificial neural networks (ANNs) have been widely used as a promising alternative approach for a forecasting task because of several distinguished features. Research efforts on ANNs for forecasting exchange rates are considerable. In this paper, we attempt to provide a survey of research in this area. Several design factors significantly impact the accuracy of neural network forecasts. These factors include the selection of input variables, prepar-ing data, and network architecture. There is no consensus about the factors. In different cases, various decisions have their own effectiveness. We also describe the integration of ANNs with other methods and report the comparison between performances of ANNs and those of other forecasting methods, and finding mixed results. Finally, the future research directions in this area are discussed.

6 Bookmarks
 · 
454 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Exchange rate prediction is an important yet challenging problem in financial time series analysis. Although the historical exchange rates can provide valuable information, other factors will also affect the prediction significantly. These factors could be numerical or non-numerical ones, which are related to politics, economics, military, or even market psychology. Previous automatic exchange rate prediction merely considers numerical data (or simply the historical rates) for predicting the next day value. In this paper, we show how to utilize and combine many related factors, both numerical and non-numerical factors, for exchange rate prediction. With an example on forecasting exchange rate between US dollar and Japanese yen, we investigate how to exploit the information from non-numerical factors. We then engage a novel integrated approach which successfully combines information obtained from both numerical and non-numerical factors. We show how to quantify the non-numerical fundamental information, provide details steps on how to construct single predictors on different kinds of information separately, and finally describe how to integrate these separate predictors. Experimental results showed that our method can achieve the Directional Symmetry (DS) accuracy of 86.96%, which is much higher than only exploiting numerical information.
    Neural Computing and Applications 01/2011; 20:945-954. · 1.76 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The estimation of state variables of dynamic systems in noisy environments has been an active research field in recent decades. In this way, Kalman filtering approach may not be robust in the presence of modeling uncertainties. So, several methods have been proposed to design robust estimators for the systems with uncertain parameters. In this paper, an optimized filter is proposed for this problem considering an uncertain discrete-time linear system. After converting the subject to an optimization problem, three algorithms are used for optimizing the state estimator parameters: particle swarm optimization (PSO) algorithm, modified genetic algorithm (MGA) and learning automata (LA). Experimental results show that, in comparison with the standard Kalman filter and some related researches, using the proposed optimization methods results in robust performance in the presence of uncertainties. However, MGA-based estimation method shows better performance in the range of uncertain parameter than other optimization methods.
    Neural Computing and Applications · 1.76 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The sports betting market has emerged as one of the most lucrative markets in recent years. Trading in sports betting markets entails predicting odd movements in order to bet on an outcome, whilst also betting on the opposite outcome, at different odds in order to make a profit, regardless of the final result. These markets are mainly composed by humans, which take decisions according to their past experience in these markets. However, human rational reasoning is limited when taking quick decisions, being influenced by emotional factors and offering limited calibration capabilities for estimating probabilities. In this paper, we show how artificial techniques could be applied to this field and demonstrate that they can outperform even the bevahior of high-experienced humans. To achieve this goal, we propose a case-based reasoning model for trading in sports betting markets, which is integrated in an agent to provide it with the capabilities to take trading decisions based on future odd predictions. In order to test the performance of the system, we compare trading decisions taken by the agent with trading decisions taken by human traders when they compete in real sports betting markets.
    Applied Intelligence 04/2013; 38(3). · 1.85 Impact Factor

Full-text (2 Sources)

View
448 Downloads
Available from
May 29, 2014