Abstract
Problem statement: Forecasting is very important in many types of organizations since predictions of future events must be incorporated into the decision-making process. In the case of tourism demand, better forecast would help directors and investors make operational, tactical and strategic decisions. Besides that, government bodies need accurate tourism demand forecasts to plan required tourism infrastructures, such as accommodation site planning and transportation development, among other needs. There are many types of forecasting methods. Generally, time series forecasting can be divided into classical method and modern methods. Recent studies show that the newer and more advanced forecasting techniques tend to result in improved forecast accuracy, but no clear evidence shows that any one model can consistently outperform other models in the forecasting competition. Approach: In this study, the performance of forecasting between classical methods (Box-Jenkins methods Seasonal Auto-Regressive Integrated Moving Average (SARIMA), Holt Winters and time series regression) and modern methods (fuzzy time series) has been compared by using data of tourist arrivals to Bali and Soekarno-Hatta gate in Indonesia as case study. Results: The empirical results show that modern methods give more accurate forecasts compare to classical methods. Chen’s fuzzy time series method outperforms all the classical methods and others more advance fuzzy time series methods. We also found that the performance of fuzzy time series methods can be improve by using transformed data. Conclusion: It is found that the best method to forecast the tourist arrivals to Bali and Soekarno-Hatta was to be the FTS i.e., method after using data transformation. Although this method known to be the simplest or conventional methods of FTS, yet this result should not be odd since several previous studies also have shown that simple method could outperform more advance or complicated methods.
Highlights
Forecasting is very important in many types of organizations since predictions of future events must be incorporated into the decision-making process
Recent studies show that the newer and more advanced forecasting techniques tend to result in improved forecast accuracy under certain circumstances, no clear-cut evidence shows that any one model can consistently outperform other models in the forecasting competition (Song, 2008)
Time series regression: Time series regression for Bali and Soekarno-Hatta are given by the following equation: For in sample, n is the number of observations (a) Additive model
Summary
Forecasting is very important in many types of organizations since predictions of future events must be incorporated into the decision-making process. The definition of the first order seasonal fuzzy time series model for forecasting proposed by Song and Chissom (1993b) is given as follows. The high order fuzzy time series model proposed by Chen (2002) is given as follows: The parameters α, β, γ should lie in the interval (0, 1). F (t-n) this fuzzy for this level, trend and seasonal component are 0.2 It is called the nth order fuzzy time series forecasting model. Step 2: Fuzzy relationship was determined according to SARIMA model for the data set This procedure has been done by Faraway and Chatfield (1998) in order to select neural network input variable. Time series regression: Time series regression for Bali and Soekarno-Hatta are given by the following equation: For in sample, n is the number of observations (a) Additive model (degree of freedom in case of SARIMA).
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call