Pronóstico postpandemia del turismo receptivo vía aérea mediante la utilización de modelos bayesianos. El caso de Colombia

This article makes a medium‐long term forecast (2023‐2030) of the inflow of foreign tourists to a country by air, using Colombia as a case study. First, we analyse how the development and application of State policies in tourism managed to boost tourism, with an emphasis on inbound tourism, over the three decades previous to the year 2019 (prior to the pandemic period). To achieve this objective, we applied a Bayesian Structural Time Series (BSTS) model, designed to work with time series data, and widely used for feature selection, time‐series forecasting, immediate prediction, and causal impact inference. Two relevant aspects can be highlighted from the results obtained: first, that the growth of future demand (inflow of non‐resident foreign tourists by air) will follow the trend shown in the immediate post‐pandemic recovery period (2022). And, secondly, the models present error values, measured using the MAPE indicator, of under 5%, which makes the BSTS method a viable alternative methodology for the calculation of tourism demand forecasts (in the medium‐long term).