Tourism Planning Meets AI: A Fuzzy-Logic and PLS-SEM–ANN Framework for Stakeholder-Centric Destination Competitiveness Forecasting

Global economic growth is fueled by tourism, which necessitates careful planning and evaluation for long-term competitiveness. This study is among the first to integrate Machine Learning (ML), Fuzzy Logic (FL), and Partial Least-Squares Structural Equation Modeling (PLS-SEM) in the context of Tourism Competitiveness (TC) and Destination Competitiveness (DC). PLS-SEM examines factor relationships, FAHP gives weighted criteria, FL controls data uncertainty, and ML improves accuracy by honing model predictions. This hybrid strategy supports data-driven decision-making by identifying important competitiveness factors. Adaptive strategies are made possible by real-time monitoring, which guarantees that destinations maintain their competitiveness in changing circumstances. The suggested framework highlights areas for improvement as well as strengths and weaknesses to help with planning, management, and marketing. Additionally, it makes benchmarking easier, which promotes healthy competition in the travel industry. The findings of the study are relevant to policymakers, managers, academicians, and destination planners working in the area of tourism analytics, regional development, and strategic competitiveness.