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
 · 
503 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Sales forecasting is very bene¯cial to most businesses. A successful business needs accurate sales forecasting to understand the market and sales trends. This paper presents a novel sales fore-casting model by integrating support vector regression (SVR) and bat algorithm (BA). Since the accuracy of SVR forecasting mainly depends on SVR parameters, we use BA for tuning these parameters because Bat is a newly introduced algorithm and has many parameters. In order to ¯nd the best set of BA parameters Taguchi method was utilized. We validated our model on four known UCI datasets. Then we applied our model in printed circuit board (PCB) sales forecasting case study. We compared the accuracy of the proposed model with Genetic algorithm (GA)–SVR, particle swarm optimization (PSO)–SVR, and classic-SVR. The exper-imental results show that the proposed model outperforms the others. To ensure the robustness of our proposed model, sensitivity analysis was also done using our model to ¯nd out the e®ects of dependent variables values on sales time series.
    International Journal of Information Technology and Decision Making 01/2013; 13(1). · 1.31 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, an integrated data characteristic testing scheme is proposed for complex time series data exploration so as to select the most appropriate research methodology for complex time series modeling. Based on relationships across different data characteristics, data characteristics of time series data are divided into two main categories: nature characteristics and pattern characteristics in this paper. Accordingly, two relevant tasks, nature determination and pattern measurement, are involved in the proposed testing scheme. In nature determination, dynamics system generating the time series data is analyzed via nonstationarity, nonlinearity and complexity tests. In pattern measurement, the characteristics of cyclicity (and seasonality), mutability (or saltation) and randomicity (or noise pattern) are measured in terms of pattern importance. For illustration purpose, four main Chinese economic time series data are used as testing targets, and the data characteristics hidden in these time series data are thoroughly explored by using the proposed integrated testing scheme. Empirical results reveal that the natures of all sample data demonstrate complexity in the phase of nature determination, and in the meantime the main pattern of each time series is captured based on the pattern importance, indicating that the proposed scheme can be used as an effective data characteristic testing tool for complex time series data exploration from a comprehensive perspective.
    International Journal of Information Technology and Decision Making 07/2013; 12(03). · 1.31 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Despite the increase in the number of non-performing loans and competition in the banking market, most of the Jordanian commercial banks are reluctant to use data mining tools to support credit decisions. Artificial neural networks represent a new family of statistical techniques and promising data mining tools that have been used successfully in classification problems in many domains. This paper proposes two credit scoring models using data mining techniques to support loan decisions for the Jordanian commercial banks. Loan application evaluation would improve credit decision effectiveness and control loan office tasks, as well as save analysis time and cost. Both accepted and rejected loan applications, from different Jordanian commercial banks, were used to build the credit scoring models. The results indicate that the logistic regression model performed slightly better than the radial basis function model in terms of the overall accuracy rate. However, the radial basis function was superior in identifying those customers who may default.
    Review of Development Finance. 01/2014;

Full-text (2 Sources)

Download
499 Downloads
Available from
May 29, 2014