Equalizing Seasonal Time Series Using Artificial Neural Networks in Predicting the Euro–Yuan Exchange Rate

摘要: The exchange rate is one of the most monitored economic variables reflecting state economy in long run, while affecting it significantly short run. However, prediction very complicated. In this contribution, for purposes predicting rate, artificial neural networks are used, which have brought quality and valuable results a number research programs. This contribution aims to propose methodology considering seasonal fluctuations equalizing time series by means on example Euro Chinese Yuan. For analysis, data these currencies per period longer than 9 years used (3303 input total). Regression carried out. There two network sets generated, second focuses fluctuations. Before experiment, had seemed that there was no reason include categorical calculation. result, however, indicated additional form year, month, day week, value measured, higher accuracy order series.