Global 50 Consumer Packaged Goods (CPG) Company In-Transit Visibility & Analytics Success Story
Challenge:
A Global 50 Consumer Packaged Goods (CPG) company averaged 25,000 North American truck shipments per month. Because there was no system in place for real-time monitoring of inventory in-transit, operation team members were unaware of real-time disruptions, rendering them unable to avoid or mitigate late or non-delivery for their customers. A new strategic cross-docking network was unable to realize high-efficiency targets because the inbound Estimated Time of Arrivals (ETAs) were inaccurate ─ reducing the number of goods that could be cross-docked. The Transportation Management System (TMS) and Enterprise Resource Planning (ERP) systems did not receive real-time information and rarely received shipment plan updates. As a result, this CPG company employed hundreds of people to make check calls to carriers, drivers, and customers to update ETAs manually. This manual process was time-consuming, error-prone, and latent. Often, disruption reports were received well after they occurred, leaving logistics teams unable to mitigate late delivery impacts.
Solution:
Savi worked with this customer to implement Savi Visibility™, our live streaming in-transit tracking and ETA solution. The CPG company asked their truck carriers to send Electronic Data Interchange (EDI) and telematics feeds to Savi, while Savi set up an automated feed from and to the CPG’s Transportation Management System (TMS) to log planned shipments.
After ingesting the data from the carriers and the TMS, Savi’s massively scalable machine learning platform began to use Artificial Intelligence (AI) to build algorithms to much more accurately predict both inbound and outbound ETAs. The Savi Visibility user interface provides map, list, and reporting views of the real-time status of all shipments. Predictive alerts, such as “Trending Late” and “Trending Early,” were determined using customer-specific thresholds of time, distance, and amount predicted late. Predictive ETAs and alerts were sent to users and the Enterprise Resource Planning (ERP) system, enabling synchronization between TMS, Warehouse Management System (WMS), and yard management operations.
Result:
With a continuous live streaming view of all shipments in transit and real-time alerts for the 5-10% of shipments that required attention, the burden on operations diminished dramatically, making far fewer check calls necessary. Planners were able to focus on mitigating or avoiding disruptions of shipments that would otherwise have arrived late.
The substantially improved inbound ETA accuracy enabled more inbound loads to be synchronized with outbound shipments, increasing the percentage of loads to be cross-docked and reaching the original efficiency target of regional cross-docking centers.
In addition, the feed from Savi’s big data platform allowed the TMS to be continuously updated with accurate ETAs, rather than a static planned ETA or late and inaccurate EDI messages, keeping both the planning, operations, and customer teams up to date in real-time.
After the new system was implemented, the CPG was able to achieve:
- 22% improvement in cross-docking efficiency and orchestration
- 17x increase in ETA accuracy
- 350+ hours/week productivity gained per transportation lane
Historical and predictive analytics helped bring about additional transportation improvements. With a robust historical ETA data by lane, carrier and distribution center, and the Savi Insight platform, our customer was able to easily view aggregated performance and benchmark those areas to investigate possible improvements holistically.
Knowing the actual average ETAs and the likely variability gives the CPG company actionable insights about in-transit inventory levels, helping them to reduce safety stock or avoid stock-outs.
Finally, early outreach and collaboration with their customers when an unavoidable disruption occurs, as well as more accurate shipment ETAs overall, has brought improved customer satisfaction.
Learn more about our solutions.