Forecasting The Tourism Demand In VIETNAM Using Time Series Analysis

Abstract

Tourism is currently the biggest industry in many countries, mainly contributed to economic activities. This study focused on predicting the tourism demand accuracy and making the tourism industry grow stably. Vietnam was chosen as the country of empirical study due to its availability of data in annual year for long range of time series. The forecast tourism demand in Vietnam is considered by the models of forecasting to analysis and predict tourism demand. In this research, the seven quantitative forecast methods including Naïve, Autoregressive model (AR), Simple exponential smoothing, Moving average (MA), ARIMA, Holt-Winter’s model, Grey model, and Neural network model was investigated. In addition to get the forecast accuracy, in term of external factors including fuel price, currency exchange rates and consumer price index is also considered to be more practical and more accuracy. Finally, outcomes from forecast models are compared based on the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE), then the most suitable forecast tourism demand in Vietnam is proposed. Keywords: Tourism demand, Grey model, ARIMA, Holt-Winter’s model, Neural Network model