The management of Cold Chain (CC) logistics is critical to ensuring the safety, quality, and integrity of perishable food products, as even minor deviations from controlled conditions can cause irreversible deterioration and economic losses. However, current monitoring practices, often manual or semi-automated, show limited capability in handling real-time data, constraining risk mitigation and regulatory compliance. The increasing adoption of Internet of Things (IoT) technologies and advanced analytics provides new opportunities to enhance visibility and control across distributed supply chains.
This paper presents TRACING (innovaTive AI fRAmework for Cold chaIN Governance), a design-oriented framework that supports governance in Cold Chain networks through the integration of Data and Process Governance. Following a design science research approach, TRACING is conceptualized as a socio-technical artifact enabling decision-making, coordination, and accountability among multiple stakeholders.
The framework comprises four components: Data Governance (data collection, validation, and quality assessment), Process Governance (process modeling, monitoring, and optimization), Data Analytics (leveraging Process Mining and Artificial Intelligence), and an event-driven architecture enabling real-time communication and interoperability. These components enable the transformation of raw sensor data into structured knowledge, supporting continuous performance monitoring and anomaly detection.
The framework is illustrated through a Cold Chain scenario involving controlled product maturation, showing how the integration of data and process perspectives enables transparency, traceability, auditability, and coordination, ultimately enhancing operational reliability and resilience.
This work bridges the gap between data infrastructures and governance requirements, providing a structured approach to support knowledge-driven decision-making in complex supply chain environments.