Supply Chain Network Analytics Guiding Food Regulatory Operational Policy

Abstract

Food adulteration poses a serious threat to public health. The U.S. Food and Drug Administration (FDA) has a major role in maintaining food safety in the U.S. through various activities including sampling of imported shipments and site inspections. However, resource constraints limit the number of these interventions, making risk-based allocation essential to ensure effectiveness. This paper aims to develops a data-driven, risk analytics approach to identify high-risk firms importing food (consignees). Leveraging supply chain analytics, based on shipment history and other data sources, network features are constructed to model risk, specifically predicting which consignees are likely to fail FDA site inspections. The approach is applied to consignees of shrimp, a product with frequent food safety problems. The main findings are that supply chain network complexity, and website network engagement, are predictive of risk. For instance, firms that import a more unusual portfolio of products, as measured through subgraph modularity on a product network graph, are more likely to fail site inspections. The results suggest that network-based risk analytics could significantly improve the effectiveness of regulatory activities related to food supply chains, and substantially increase the number of failed site inspections and imported shipment samples.