Emerging Rural Destinations: Multimethod Approach to Decode What Drives Consumer Behavior

The current study aims to integrate the tourist perspective from both supply and demand sides in predicting consumer satisfaction and loyalty in rural tourism. Grounded in the push–pull framework, the research develops a conceptual model and employs a multimethod approach for validation. Structural equation modeling (SEM) and two machine learning techniques—artificial neural networks (ANN) and random forest (RF)—are utilized to ensure robustness in analysis. The findings reveal that both destination image (DI) and memorable tourism experience (MTE) directly impact destination loyalty. Additionally, consumer perception of community interaction (CPCI) positively influences satisfaction but does not have direct effect on destination loyalty. However, CPCI impacts destination loyalty indirectly forming a sequential mediation through MTE, DI, and SAT. The key findings from machine learning (ML) technique suggest consumer expectation as the most crucial determinant. Practically, this study provides several recommendations to rural tourism practitioners about how to use the determinants of rural tourism and identifies moderators to lure tourists to visit the destination.