Tourism dynamics in South-East Europe: Similarities and predictability

Purpose - This study investigates the dynamics and common tourism patterns of selected countries in South-East Europe in the post-COVID-19 period. The main goal is to classify the countries by inter-country similarities and differences in tourist flows while assessing predictability in tourism demand across the region. Methodology - The research analyzes monthly tourist arrivals for the period 2022-2025 in Albania, Bosnia and Herzegovina, Bulgaria, Croatia, Greece, Montenegro, North Macedonia, Serbia, and Slovenia. It employs K-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering to identify time series patterns, while a Seasonal AutoRegressive Integrated Moving Average (SARIMA) panel data model provides a one-year forecast to 2026. Findings - Results reveal three groups: Cluster 0 (Albania, Bulgaria, Croatia, North Macedonia, Slovenia) with similar patterns; Cluster 1 (Bosnia and Herzegovina, Greece, Montenegro); and Serbia as an outlier. Seasonality is lowest in Serbia and highest in Albania and Bulgaria. Forecasts predict the largest growth in Albania (21%), moderate gains in Bosnia and Herzegovina, Bulgaria and Montenegro (6-8%), modest increases in Serbia and Greece (2-3%), slow growth for Croatia (1%) and stagnation for North Macedonia. Implications - This research advances the literature on regional tourism forecasting and supports policymakers in targeting low-seasonality destinations for stable planning and high-growth areas for capacity expansion, enhancing tourism resilience of South-East Europe.