FORECASTING THE NUMBER OF SPORT TOURISM ARRIVALS IN SOUTHWEST BULGARIA

This paper presents an application of some forecasting methods concerning sport tourism arrivals in Southwest Bulgaria: linear trend forecasting, double exponential forecasting (Holt’s method), triple exponential forecasting (the Holt-Winters Method), and the ARIMA method. A specially designed model for estimating the weight coefficient needed for determining the size of the sport tourism’s sector in the time series of the available data and in the forecast values is presented. In order to test the forecasting methods and produce forecasts up to the year 2030, a time series and past period predictions have been constructed based on statistical records since 1964. Several major problems in the application of the exponential smoothing methods for the purpose of the long-run forecasting and the needs of the sport tourism subsector of Bulgaria tourism industry are addressed. These problems include (a) finding a suitable general indicator, (b) calculating short-term and long-term forecasts, (c) comparing the results of the forecast techniques on the basis of the errors in the forecasts, (d) estimating the size of the sport tourism in Southwest Bulgaria in certain terms so that the forecast(s) of the above-mentioned general indicator could be particularized especially for examined sub-sector and region. The results from the different forecasting methods and techniques are presented and conclusions are drawn regarding the reliability of the forecasts.