Predictive decision support for underutilization risk in public sector tourism: Evidence mapping and a design science roadmap

Publicly funded tourism assets can become stranded when utilization persistently falls below a reasonable level relative to capacity or policy-defined potential. Yet tourism analytics research largely forecasts demand or composite performance and seldom formalizes underutilization as a governance outcome, nor evaluates decision quality within planning and budgeting workflows. This study (i) maps recent evidence and research gaps and (ii) proposes a conceptual artefact in the form of a policy-ready methodology and roadmap for developing a predictive decision support system (DSS) to mitigate underutilization risk. An evidence-mapping review of 117 Scopus-indexed studies (2021–2026) reveals a critical gap: 0% of the analyzed studies explicitly formalize "underutilization" as a policy outcome in their titles. Furthermore, evaluation procedures remain opaque, with 79.5% of studies failing to clearly specify their methodologies. In response, we outline a design-science roadmap for an auditable predictive DSS that operationalizes underutilization through two complementary metrics: the Underutilization Gap (UG) and the Utilization Ratio (UR). The proposed architecture integrates heterogeneous tourism, spatial, and socio economic data while providing traceable audit trails via Explainable AI (XAI) to ensure scores are logically defensible in public budgeting. Crucially, the framework introduces a two-layer evaluation that couples technical predictive performance (E1) with decision-utility metrics (E2), such as rank agreement and allocation efficiency. This methodology equips local governments with a practical, theoretically grounded instrument to justify prioritization, optimize resource allocation, and reduce the likelihood of underutilization-related policy failure.