Data-Efficient Traceability Analytics for Food Supply Chains: Integrating Adaptive Monitoring, Edge Intelligence, and Blockchain Records
Main article
Abstract
Food supply chains increasingly rely on digital traceability systems to document origin, handling conditions, custody changes, and quality-related events. However, the operational value of traceability is often limited by an imbalance between excessive data capture and insufficient evidential clarity. Continuous Internet-of-Things sensing creates large volumes of temperature, humidity, location, shock, and process data, while blockchain systems are not designed to store high-frequency raw streams directly. This article develops a data-efficient traceability analytics framework that integrates adaptive monitoring, edge intelligence, and blockchain records for food supply chains. The framework separates operational monitoring from audit-oriented recording: edge devices preprocess sensor data, detect contextual risk, and select evidence segments, while blockchain records preserve critical state transitions, cryptographic hashes, compliance events, and access permissions. A simulated cold-chain and processing dataset is used to compare static monitoring, event-only logging, and adaptive edge recording. The results indicate that an adaptive edge strategy can reduce stored data volume by more than 70% relative to static one-minute sampling while maintaining high recall of critical events and improving audit reconstruction. The study contributes to business and data analytics by translating traceability from a passive record-keeping function into an intelligent decision infrastructure. It also provides managerial guidance on data governance, blockchain deployment, platform interoperability, and risk-sensitive monitoring design in food supply chains.
