This study proposes a novel framework integrating generative AI and machine learning classifiers to tackle heterogeneous multi-criteria group decision-making (MCGDM) problems. The methodology consists of four structured phases: data collection, feature extraction, classifier training, and decision optimization.
By combining generative AI's ability to simulate realistic alternatives with the classification strengths of machine learning, this approach improves accuracy and adaptability in complex decision-making scenarios across domains like healthcare, engineering, and urban planning.
The fusion enhances computational efficiency and reduces human bias, offering a generalizable solution framework for real-world applications involving varied data sources and decision criteria.
