Tourism is pivotal for economic growth worldwide, necessitating effective planning and assessment in the competitive industry for sustainable development. Integrating machine learning and fuzzy logic into these processes has shown promise in capturing intricate tourism data. This study proposes a novel approach, merging machine learning, fuzzy logic, and PLS-SEM, to model the tourism perspective for destination competitiveness. It uses fuzzy logic to handle data uncertainty, assigning weights via Fuzzy AHP, and applies PLS-SEM to assess relationships between factors impacting competitiveness. Machine learning refines the model, enabling accurate evaluations. This approach identifies key drivers and indicators of competitiveness, aiding planners and policymakers in making data-driven decisions. It offers real-time monitoring and adaptive planning by continuously analysing the evolving tourism landscape. The framework holds implications for planning, management, and marketing, providing insights into strengths, weaknesses, and areas for enhancement. It also assists in benchmarking and promoting healthy competition.