Wykorzystanie metod wygładzania wykładniczego do prognozowania kursu sprzedaży EUR

Abstract

The principal aim of the paper was to use exponential smoothing methods for forecasting EUR selling rate. Forecasting models were built on the basis of data from the period from January 2010 to April 2013, obtained from the website of the National Polish Bank. The important objective of the study was to use the simplest exponential smoothing methods. Another important element of the study was the conduct of a comparative analysis of the quality of forecasts. To assess the quality of forecasts, six measures of statistical description were used: mean error, mean absolute error, maximum absolute error, root mean square error, mean absolute percentage error, median absolute percentage error and maximum absolute percentage error.