Strategic Decision-Making Enhancement through Graph-Optimized DEMATEL-AHP with Pruning

In traditional decision-making methods such as AHP and DEMATEL, the determination of key parameters heavily relies on expert judgment, leading to issues of subjectivity and inconsistency. For instance, in supply chain management, subjective parameter selection can lead to suboptimal resource allocation, while in public policy formulation, it may result in biased or misinformed decisions. These issues hinder the reproducibility and reliability of decision outcomes. Specifically, the hierarchical structure in AHP is determined without a clear quantitative method, and the establishment of thresholds in DEMATEL often lacks objectivity, which can result in less reliable and controllable networks. This subjectivity not only limits the accuracy of the decision-making process but also hinders the repeatability of the results. To overcome these limitations, this paper proposes an innovative integration of DEMATEL and AHP. By combining the causal analysis capabilities of DEMATEL with the hierarchical structuring strengths of AHP, the proposed model not only enhances the objectivity of factor weighting but also improves the overall interpretability of the decision-making process. This integrated approach allows for more reliable identification of key causal relationships and prioritization of factors, offering decision-makers a more robust framework for complex strategic decision-making. Furthermore, this paper introduces statistical techniques to minimize residual errors and applies pruning mechanisms for enhanced stability, ultimately addressing the challenges of subjectivity and inconsistency in traditional methods.