Fusion of human-driven and data-driven decision models: A systematic review of hybrid MCDM-AI frameworks for operations management
Franklin Open, cilt.17, 2026 (Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 17
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.fraope.2026.100801
- Dergi Adı: Franklin Open
- Derginin Tarandığı İndeksler: Scopus
- Anahtar Kelimeler: Advanced analytics, Artificial intelligence, Multiple-criteria decision making (MCDM), Operations management, Systematic literature review
- İstanbul Gelişim Üniversitesi Adresli: Evet
Özet
This systematic literature review examines hybrid decision-making frameworks that integrate human-centric multi-criteria decision-making (MCDM) methods with artificial intelligence and advanced analytics (AI/AA) in operations management. Based on 849 Scopus-indexed journal and review articles published between 2010 and 2025, the study maps the evolution of this rapidly growing field, identifies its major thematic structures and application areas, and highlights the most prevalent methodological pairings. The review shows that the literature has expanded significantly in the 2020s, with strong geographical concentration in Asia and the Middle East, alongside substantial contributions from Europe and North America. Core themes centre on decision making, multi-criteria analysis, and optimization, while the data-driven components commonly include machine learning, neural networks, metaheuristic optimization, and predictive analytics. The most frequently used named MCDM methods are the Analytic Hierarchy Process (AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), which are frequently combined with metaheuristic optimization techniques. Application areas are strongly linked to sustainability, particularly in sustainable supply chains, energy systems, and environmental risk assessment. The review also finds that uncertainty is often handled implicitly or through fuzzy approaches, while robust stochastic and grey methods remain less common. Overall, the paper concludes that hybrid MCDM frameworks incorporating AI and advanced analytics offer valuable support for complex operations-management problems, but future research should strengthen uncertainty modelling, evaluation metrics, and robustness analysis.