Machine Learning Model to Reduce Manual Data Corrections in Freight Rail Tracking Systems.

Abstract

"The Freight Rail-Cargo Tracking system represents a pivotal evolution in the logistics and transportation industry. Historically, the movement of goods via rail has been integral to global trade, providing a cost-effective and efficient means of transport. However, with the advent of technology, the need for real-time monitoring and tracking of cargo became paramount. The Freight Rail-Cargo Tracking system emerged as a solution to address the challenges of ensuring timely delivery, preventing theft, and optimizing the rail network's efficiency. Leveraging advanced technologies such as GPS, RFID, and IoT sensors, this system offers stakeholders, including shippers, consignees, and logistics providers, unprecedented visibility into the location, condition, and status of freight in transit. According to my research into this area, I found despite the rapid evolution and adoption of advanced technologies, many industries continue to rely on legacy messaging systems for critical operations, including Electronic Data Interchange (EDI). These legacy systems, often built decades ago, were not designed to handle the volume, complexity, and real-time requirements of today's digital landscape. Issues such as data inaccuracies, transmission errors, and delays can arise, undermining the efficiency and reliability of supply chain operations. To overcome these challengers, Rail-cargo tracking system owned companies rely on a employing a vast team for manual data corrections. Relying on manual interventions can limit the real-time visibility and responsiveness required in dynamic freight rail operations, impacting customer satisfaction and service levels. In this study, I aim to minimize manual data corrections and pinpoint essential manual interaction data points for stakeholders, thereby reducing time and costs while enhancing efficiency."