Leveraging genetic algorithms and system dynamics for effective multi-objective policy optimization: a case study on the broadcasting industry

Abstract

Complex sociotechnical systems with multiple competing objectives and nonlinear dynamics pose significant challenges for policy optimization. Traditional simulation-based methods often struggle with high-dimensional policy spaces. This study addresses these challenges by combining genetic algorithms (GAs) with system dynamics (SD) modeling to optimize policy configurations in complex environments. Our approach merges SD’s capacity to simulate intricate system behaviors with GA’s prowess in multi-objective optimization. The SD model uses predefined decision variables to simulate system behavior, while GA iteratively adjusts these variables to find optimal policy configurations. We apply this hybrid approach to a media industry case study, focusing on balancing profit, competitiveness, and audience satisfaction. The research methodology integrates SD’s ability to capture complex system behaviors with GA’s strength in optimizing multiple objectives. An SD model simulates system behavior based on predefined decision variables representing key policy levers. GA then iteratively adjusts these variables based on fitness objectives derived from the SD model. This process evaluates performance and identifies the globally optimal policy configurations. The results show that the hybrid SD–GA framework significantly improves policy solutions compared to conventional methods. Sensitivity analysis confirms the optimized policies’ robustness and comparative assessments highlight our approach’s advantages in navigating complex policy spaces. This study introduces a new SD–GA framework that improves data-driven policy formulation in complex systems. It combines policy informatics and evolutionary algorithms to offer a comprehensive approach to multi-criteria decision-making. Future research could include long-term validation of this approach in the broadcasting industry to further refine and apply this methodology across various domains.