Forecasting inbound tourist arrivals to Iran post-COVID-19 pandemic: a small data approach using grey models

Purpose This study aims to apply and compare various grey forecasting models to forecast the number of inbound tourists to Iran from 2024 to 2026, using data from 2020 to 2023. The goal is to identify the most accurate model for forecasting post-COVID-19 tourism trends, thereby aiding policymakers and industry stakeholders in strategic planning. Design/methodology/approach Six grey forecasting models: GM (1,1), RGM (1,1), Unbiased GM (1,1), modified unbiased GM (1,1), DGM (1,1) and Grey Verhulst, were implemented using Python programming. Given the challenges posed by the COVID-19 pandemic, which rendered previous historical data invalid, the models are selected to work effectively with the small data available for the post-pandemic period. The performance of these models was evaluated based on their forecasting accuracy, utilizing mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE). Findings The GM (1,1) model demonstrated the highest forecasting accuracy, with the lowest MAE and RMSE, and, making it the most suitable model for forecasting inbound tourist numbers in this study. In contrast, the DGM (1,1) model showed a tendency to overestimate future arrivals, reflected in its high error metrics. Originality/value This study offers a novel application of grey forecasting models in the tourism sector, focusing on forecasting inbound tourist arrivals during the post-COVID-19 era, a period marked by significant uncertainty and limited data. By comparing six advanced grey forecasting models, this research demonstrates their capability to address small data challenges in tourism forecasting. The findings provide a solid foundation for model selection and broaden the application of grey models within the tourism industry, delivering valuable insights for researchers and practitioners tackling similar forecasting challenges.