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 the state ofthe economy in the long run, while affecting it significantly in the short run. However, predictionof the exchange rate is very complicated. In this contribution, for the purposes of predicting theexchange rate, artificial neural networks are used, which have brought quality and valuable results ina number of research programs. This contribution aims to propose a methodology for consideringseasonal fluctuations in equalizing time series by means of artificial neural networks on the exampleof Euro and Chinese Yuan. For the analysis, data on the exchange rate of these currencies per periodlonger than 9 years are used (3303 input data in total). Regression by means of neural networks iscarried out. There are two network sets generated, of which the second one focuses on the seasonalfluctuations. Before the experiment, it had seemed that there was no reason to include categoricalvariables in the calculation. The result, however, indicated that additional variables in the form ofyear, month, day in the month, and day in the week, in which the value was measured, have broughthigher accuracy and order in equalizing of the time series.