Intelligent hybrid decision support systems for education policy and institutional performance optimization

The rapid evolution of digital technologies has accelerated the transition toward Education 5.0, where intelligent systems support advanced learning environments and data-driven institutional management. However, selecting the most effective educational technologies remains a complex decision-making problem due to uncertainty, conflicting criteria, and the involvement of multiple stakeholders. To address this challenge, this study proposes an intelligent hybrid decision-support framework based on picture fuzzy sets to manage uncertainty and hesitation in expert evaluations. The model integrates a mutual induction-based feature selection mechanism to identify the most influential criteria and determine their relative importance by capturing interrelationships among features. A novel distance and similarity measure for picture fuzzy information is also introduced to improve discrimination and accuracy in the evaluation process. The optimized criteria and weights are incorporated into a ranking procedure based on PROMETHEE II to evaluate and prioritize emerging Education 5.0 technologies. A real-world case study inspired by China's smart education transformation is conducted, assessing ten advanced educational technologies, including artificial intelligence learning systems, learning analytics platforms, and immersive learning environments. Furthermore, Monte Carlo simulation is applied to assess uncertainty propagation and stochastic behavior, while robustness is evaluated by comparing the results with traditional methods such as TOPSIS, VIKOR, MOORA, MABAC, WASPAS, EDAS, and ARAS. The results demonstrate the superior stability and reliability of the proposed framework, providing actionable guidance for policymakers and educational institutions in strategic technology adoption.