Exploring probabilistic patterns in illicit trade drivers using Bayesian belief networks: An analysis of associations with global supply chain risk

• Bayesian Belief Networks quantify probabilistic links in illicit trade drivers • Economic and institutional factors strongly shape supply chain risk patterns • Operational weaknesses in supply chain intermediaries drive vulnerability • Cluster analysis reveals conditional interdependencies among risk drivers • Findings support integrated policy and operational risk management strategies Illicit trade presents a complex and persistent threat to global economic stability and supply chain resilience. However, the mechanisms linking its underlying drivers to broader national risk environments remain insufficiently understood. This study explores probabilistic patterns in the interactions among economic, regulatory, and operational conditions to examine exposure to illicit trade and supply chain risk across 158 countries in 2025. Using data from the TRACIT Illicit Trade Index and the CountryRisk.io supply chain risk dataset, the analysis applies a Bayesian network framework to identify likely associations rather than causal effects among six key drivers: taxation and economic environment, regulatory and enforcement quality, criminal enablers, trade and border integrity, supply chain intermediaries, and sectoral illicit trade indicators. The results indicate that strong economic and fiscal environments are associated with resilience, whereas weaknesses in supply chain intermediaries and border oversight represent primary pathways to vulnerability. Moreover, sectoral and institutional weaknesses interact through probabilistic interdependencies, amplifying systemic risk. By integrating probabilistic modelling with a risk governance perspective, this study provides actionable insights for policymakers and managers, including strategies to strengthen institutional capacity, enhance operational oversight, and implement integrated risk management approaches to mitigate illicit trade exposure. This approach demonstrates the value of exploratory pattern identification for understanding complex, multidimensional threats to global supply chains.