An integrated MCDM model with enhanced decision support in transport safety using machine learning optimization

Abstract

Having the capacity to effectively manage multi-criteria decision-making (MCDM) issues with considerable reliability is a crucial prerequisite for any MCDM model. This study introduces an advanced MCDM model that integrates logarithmic percentage change-driven objective weighting (LOPCOW), multi-objective optimization on the basis of a ratio analysis plus the full multiplicative form (MULTIMOORA), and density-based spatial clustering of applications with noise (DBSCAN). The goal is to provide robust decision support. Specifically, the model incorporates a machine learning tool, namely, grid search, to optimize the parameters of neighborhood radius (ε) and the minimum number of points, which significantly influence the clustering quality of DBSCAN. Subsequently, the cluster centers determined by DBSCAN serve as initial points for k-means clustering to negate the impact of outliers. This approach addresses the failures of DBSCAN in nearest neighbor search and parameter selection, and it also resolves the limitations of k-means related to the uncertainty in cluster outcomes due to varying initial centroid selections. Utilizing a real case study from the European Union, comprehensive comparisons of the model results demonstrate the adaptability, reliability, and stability of the proposed model, affirming its effectiveness in providing credible policy recommendations and practical decisions. Overall, this study presents policymakers, professionals, and administrators with a reliable decision-making system for conducting real-world MCDM tasks with enhanced confidence and robustness.