TIn this paper, the Chilean tourism demand experienced during the period 2000‑2018 has been modelled using a linear regression model with dichotomous variables (MRL) and an ARIMA model with a seasonal component (SARIMA). The results show that the SARIMA approach is more effective in replicating the non‑stationary, non‑linear behaviour and the presence of seasonality in the series, with the forecasts obtained from this model presenting a low rate of error, in this case ‑5.6% for outbound tourism and ‑5.9% for inbound tourism. In consequence, this approach may be an effective tool for forecasting forecast tourism demand in the short term, and support for planning and management in the sector in the face of fluctuations in tourism demand.