Bayesian Supply Chain Tracking Using Serial-Level Information

Supply chain visibility is one of the main levers for achieving operational efficiency. Modern supply chain tracking systems can deliver serial-level information about the location of items progressing through the chain. However, these systems still fail to meet the managers´ visibility requirements in full, since they provide discrete information about product location at specific time instances only. This paper proposes a model that uses the data provided by these tracking systems to deliver enhanced tracking information to the final user. Following a Bayesian approach, the model produces realistic continuous estimates about the current and future locations of products across a supply network, taking into account the characteristics of the product behavior as well as the configuration of the data-collection points. These estimates can then be used to optimize operational decisions that depend on product availability at different locations. This paper demonstrates how the proposed model can enhance tracking information delivered by the radio frequency identification (RFID) technology and the electronic product code (EPC) network. The enhancement of tracking information quality is highlighted through an example.