Research Information System
Engineering Applications of Artificial Intelligence, vol.163, 2026 (SCI-Expanded, Scopus)
This study presents an intelligent decision-support framework for addressing the Projects–Bidders Matching (PBM) problem in public procurement, designed to handle heterogeneous and uncertain information. The approach employs fuzzy set theory, through triangular fuzzy numbers, intuitionistic fuzzy sets, and linguistic evaluations, to capture vagueness, hesitancy, and imprecision in expert judgments. To determine the relative importance of criteria from project and bidder perspectives, we employ a hybrid weighting mechanism that combines deviation from a reference point with entropy-based measures to derive data-driven weights. By combining fuzzy modeling, objective weighting, and behavioral decision theory within an artificial intelligence framework, the model enhances explainability and supports data-driven decision-making under uncertainty. From an engineering perspective, the framework is applied to optimize bidder assignments in real-world Indian public procurement scenarios. A multi-objective optimization model is formulated to (i) maximize cumulative prospect values that jointly reflect individual preferences and socially influenced preferences for both bidders and projects, (ii) minimize the absolute deviation between these cumulative prospect values, ensuring fairness, transparency, and alignment and (iii) satisfy a stability constraint to ensure that no bidder–project pair has an incentive to deviate from the assigned matching. The framework’s effectiveness is demonstrated through a practical case study, and its robustness is validated through extensive sensitivity and variation analyses.