Spatial coupling between historic buildings and tourism development in China’s historical and cultural cities

Historic buildings are an important category of built heritage, but evidence on their coordination with tourism is often based on local cases. Of 143 candidate city-level units, 127 were retained after screening. This study examines 1176 historic-building records and their relationships with domestic and international tourism. The analysis combines spatial analysis, a coupling coordination degree (CCD) model, repeated nested cross-validation, province-grouped validation, and SHAP interpretation of held-out Random Forest predictions. Scale sensitivity is substantial: population-normalized CCD matches baseline classes in 35.4% of domestic and 48.8% of international cases, versus 76.4 and 83.5% under administrative-area normalization. Thirty-six cities (28.3%) shift high/low resource–tourism typology between markets. Predictive generalization is weak: across 100 outer folds, Random Forest yields R ² = 0.028 ± 0.228 domestically and 0.065 ± 0.223 internationally, with negative province-grouped R ². Held-out SHAP rankings are most stable for CLCD/DEM domestically and GDP/SHDI internationally, supporting cautious, non-causal interpretation.