Forecasting China's outbound travel recovery post-COVID-19

Abstract

With historic data losing most of its value following shocks, this paper proposes a novel approach to combine counterfactual forecasts with a diffusion process to generate monthly recovery forecast of Chinese outbound tourism post-COVID-19. The counterfactual forecast uses a combination forecasting method based on temporal aggregation. Recovery rate forecasts follow a gradual diffusion process, used to scale the counterfactual forecast, resulting in the final prediction. The strength of this approach lies in its capacity to combine outputs from a conventional forecasting model with a theoretical framework that describes the evolution of a tourism destination as a sigmoid curve. It delivers remarkable accurate interval forecasts and offers a flexible framework that can be adapted to different contexts and decision horizons.