Real-time data insights are transforming logistics performance, driving down costs and improving CO2 emissions management. Adding Artificial Intelligence (AI) to Transport Management Systems (TMS) is set to further enhance the depth and breadth of data, extending automation and enhancing predictive insights, as Elmer Spruijt (pictured), VP, Global Sales, Descartes explains…
Real-Time Visibility
The growing availability of real-time data throughout global supply chains is transforming operational performance. Real-time shipment tracking is allowing companies to automatically update end customers with accurate delivery timescales. Immediate access to a global logistics network provides a real-time view of carrier options, facilitating next level decision making based on costs, timing, performance record, even CO2 emissions. Used in tandem with a Transport Management System (TMS), real-time data can drive automation, such as carrier confirmation and the creation of relevant transport documents, as well as customer updates.
Of course, in a complex, multi-layered global logistics network, data gaps are inevitable, which is where the addition of AI into this process is set to deliver significant benefits. For example, when a truck’s telematics device goes offline for any reason, the back-up information is provided via a mobile app. If, however, the driver has not downloaded the app, the vehicle cannot be tracked. Using an AI agent to automatically contact the driver and request installation is a simple, cost-effective process that quickly resolves any data gaps.
Streamlining and Automating
A similar approach can be used if a carrier’s data feed is compromised. An AI agent automatically contacting the carrier to request a network reset, as well as any specific missing information, such as proof of delivery, that got lost during the glitch, can seamlessly resolve the issue.
While these processes could in the past have been undertaken manually, in an industry enduring tight margins and significant disruption, this has rarely been a cost-effective option. Yet with customer invoicing increasingly automated and prompted by proof of delivery, any missing tracking data can result in payment delay. The closer organisations can move towards 100% shipment tracking throughout every journey, the more automation can be achieved, further improving efficiency and reducing the need for manual exceptions management.
Expanding Business Value
Furthermore, AI can also help to improve the depth of Scope 3 emissions reporting, building on the existing insight provided by a TMS about the CO2 generated by each vehicle based on a number of factors, including size, weight, distance and speed. Where vehicle specific information is not available, and the TMS defaults to generic estimates, the addition of AI to this process allows the system to explore more data sources, adding greater accuracy to the emissions assessment process.
AI is also set to play a key role in combating the escalating risk of freight fraud. Measures such as enhanced carrier vetting and onboarding are key to improving the verification of carriers, monitoring insurance and preventing fraud.
Conclusion
The adoption of AI throughout the transport management industry is at an early stage. But the significant on-going investment now, building on the value of real-time data resources to improve efficiency, add automation and enhance predictive analytics is compelling. For those organisations still reliant on out-dated systems and intermittent data updates, the gulf in agility and resilience is becoming a concern. As AI adds ever more valuable intelligence to efficient transport management, the adoption of innovative technology is delivering a step change in competitive advantage.
