Radial Basis Function Neural Network and Prediction of Exchange Rate
This study aims to predict the exchange rat based on radial basis function neural network (RBFNN). Concerning the selected sample point, it only responds to the inputs of neighboring samples and hence has better approximation performance and overall optimization than other forwarding networks, in addition to being simple in structure and fast in training speed. RBFNN in empirical risk minimization methods has been studied, their adaptability to exchange rate prediction has been explored, and these methods have been verified by exchange rate data. The contributions are proposing an exchange rate prediction algorithm based on RBFNN and more accurately predicting short-term and long-term exchange rate variation trends.
KeywordsRadial basis function Neural network Prediction
This research was supported by the Education Department of Fujian Province, China (Grant number: JZ160491); Social Science Fund of Fujian Province, China (Grant number: FJ2018B075); Fuzhou University of International Studies and Trade (Grant number: 2018KYTD-14).
- 7.Carvalho, G.R., Brandão, D.N., Haddad, D.B., do Forte, V.L., Ceddia, M.B.: A RBF neural network applied to predict soil field capacity and permanent wilting point at brazilian coast. In: IEEE 2015 International Joint Conference on Neural Networks, pp.1–5 (2015)Google Scholar
- 8.Li, X., Deng, Z.: A machine learning approach to predict turning points for chaotic financial time series. In: 19th IEEE International Conference on Tools with Artificial Intelligence, vol. 2, pp. 331–335(2007)Google Scholar