Forecasting tourism growth with State-Dependent Models

We introduce two forecasting methods based on a general class of non-linear models called ‘State-Dependent Models’ (SDMs) for tourism demand forecasting. Using Monte Carlo simulation which generated data from linear and models, we evidence how estimations SDMs can capture the level shifts pattern nonlinearity in data. Next, apply new to forecast growth Japan. The forecasts are compared with classical recursive SDM forecasting, Naïve ARIMA, Exponential Smoothing, Neural Network Time varying parameters, Smooth Transition Autoregressive regression model dummy variables. find that improvements proposed SDM-based more pronounced longer-term horizons. • Demonstrate effectiveness State Dependent (SDM) through Forecast evaluation Japan's Compares several nonlinear Introduced three variants Improved grid-searching smooth