Title :
Wavelet based forecasting approach, with application
Author :
Almasri, Abdullah ; Locking, Hakan ; Shukur, Ghazi
Author_Institution :
Dept. of Econ. & Stat., Vaxjo Univ., Vaxjo, Sweden
Abstract :
In this paper we outline a framework for forecasting using maximal overlap discrete wavelet transform (MODWT) based multiresolution analysis (MRA). This framework has been applied for forecasting the tourism arrival series from Denmark to Norway. We compare forecasted values obtained from modeling the data in the time domain with the forecasted values from the wavelet domain using the traditional Box-Jenkins methodology. In both cases, diagnostic tests have been conducted to insure the specification of the model. The results have shown that the wavelet based forecasts outperforms the traditional Box-Jenkins approach in term of forecasts accuracy.
Keywords :
discrete wavelet transforms; forecasting theory; travel industry; Box-Jenkins methodology; Denmark; Norway; maximal overlap discrete wavelet transform; multiresolution analysis; tourism arrival series; wavelet based forecasting approach; Demand forecasting; Econometrics; Economic forecasting; Fluctuations; Fourier transforms; Multiresolution analysis; Predictive models; Statistics; Wavelet analysis; Wavelet transforms; MODWT; MRA; WaveForecasting; Wavelet;
Conference_Titel :
Financial Theory and Engineering (ICFTE), 2010 International Conference on
Conference_Location :
Dubai
Print_ISBN :
978-1-4244-7757-9
Electronic_ISBN :
978-1-4244-7759-3
DOI :
10.1109/ICFTE.2010.5499417