Synthetic multi-criteria decision analysis (S-MCDA): A new framework for participatory transportation planning

Participatory multi-criteria decision analysis plays a vital role in transportation planning by integrating diverse stakeholder views and balancing conflicting objectives. However, it faces high costs, time demands, and coordination difficulties. This paper introduces the Synthetic Multi-Criteria Decision Analysis (S-MCDA) framework, which utilizes large language models to generate synthetic actors to support participatory decision-making in transportation planning. A literature review combining bibliometric and content analysis highlights current methods across logistics, road, rail, maritime, and transit sectors. Based on these findings, the S-MCDA framework addresses stakeholder complexity and streamlines tasks like structuring analyses, eliciting preferences, and evaluating results. While the framework has the potentially to significantly improve consistency and decision quality, it raises concerns regarding computation, ethics, and AI over-reliance. Thus, the paper offers best practices for managing data quality, reducing bias, ensuring human oversight, and promoting transparency. Future research should further explore the use of synthetic agents to support collaborative decision-making in complex transport systems.