47-67

Research papers

• Ψυλλάκης, Ζαχαρίας
• Παναγόπουλος, Αλκιβιάδης
• Κανελλόπουλος, Δημήτρης Ν.

This paper establishes a low cost inferential model that allows reliable time seriesforecasts. The model provides a naive unique computationally straightforwardapproach based on widely-used additive models. It refers to the decomposition ofevery time series value in “random” components, which are compounded toconstitute a “Fibonacci type” predictor random variable. The expected value ofthis predictor gives a forecast of a future time series value. The standarddeviation of the predictor serves to construct a prediction interval at a predefinedconfidence level. The major features of our model are: forecasting accuracy,simplicity of the implementation technique, generic usefulness, and extremely lowcost effort. These features enable our model to be adopted by tourismpractitioners on various types of forecasting demands. In this paper, we presentan application study to forecast tourism demand that exists in the Greekaccommodation industry (i.e. in Greece and in the broad region of Athens). In theapplication study, two independent approaches have been adopted. In the firstapproach we implemented our model, and in the second approach weimplemented the well-known Box-Jenkins method.

• Economics and Business

• Τουρισμός

time series, forecasting models, Naïve models, ex-post and ex-ante forecasts, forecast accuracy and validation, tourism demand

Περιέχει σχήματα, πίνακες, βιβλιογραφία και παράρτημα