Title :
Would evolutionary computation help in designs of ANNs in forecasting foreign exchange rates?
Author :
Chen, Shu-Heng ; Lu, Chun-Fen
Author_Institution :
Dept. of Econ., Nat. Chengchi Univ., Taipei, Taiwan
Abstract :
This paper evaluates the relevance of evolutionary artificial neural nets to forecasting the tick-by-tick DEM/USD exchange rate. With an analysis based on modern econometric techniques, this time series is shown to be a complex nonlinear series, and is qualified to be a challenge for ANNs and EANNs. Based on the five criteria, including the Sharpe ratio and a risk-adjusted profit rate, we compare the performance of 8 ANNs, 8 EANNs and the random-walk model. By the Granger-Newbold test, it is found that all neural network models can statistically beat the RW model in all criteria at the 1% significance level. In addition, among the 16 NN models generated in different designs, the best model is the EANN with the largest search space
Keywords :
economic cybernetics; evolutionary computation; foreign exchange trading; neural nets; time series; Granger-Newbold test; Sharpe ratio; complex nonlinear series; econometric techniques; evolutionary artificial neural nets; evolutionary computation; foreign exchange rate forecasting; neural network models; performance; random-walk model; risk-adjusted profit rate; search space; significance level; tick-by-tick DEM/USD exchange rate forecasting; time series; Artificial neural networks; Econometrics; Economic forecasting; Evolutionary computation; Exchange rates; Finance; Neural networks; Testing; Time series analysis; Transfer functions;
Conference_Titel :
Evolutionary Computation, 1999. CEC 99. Proceedings of the 1999 Congress on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5536-9
DOI :
10.1109/CEC.1999.781935
