Combining reusable packaging and AI can significantly enhance supply chain sustainability and efficiency, as Justin Newell, CEO of INFORM North America, discusses below. Reusable packaging cuts down on single-use materials, saving costs and reducing carbon footprints. These containers, being standardized, improve stacking and storage efficiency, while their sturdiness decreases product damage.
AI enhances this system by ensuring optimal container availability, reducing transportation costs, and improving demand forecasting. The complex logistics of managing vast networks of reusable assets is streamlined by AI, which integrates data from various tracking technologies to optimize container movements, minimize losses, and forecast needs accurately. Ultimately, AI can transform data overload into actionable insights, automate high-volume decisions, and, combined with human expertise, deliver optimal supply chain management and decision-making. – Ed.
Author profile: Justin Newell is the CEO of INFORM North America. He is passionate about optimizing business processes with INFORM’s hybrid AI technology. Prior to joining INFORM as COO in 2019, Newell held successful management and executive roles at leading brands such as Porsche Cars North America Inc, Reliable Carriers and Genuine Parts Company (NAPA).
Container and reusable packaging management can dramatically improve supply chain sustainability. For instance, reusable packaging eliminates the need for the continuous acquisition of single-use materials, leading to long-term cost savings and reduced carbon footprints. In addition, reusable containers typically come in standardized sizes that facilitate efficient stacking and storage in warehouses, wasted space is minimized while operational efficiencies are maximized via consistency in sizing. The use of Artificial Intelligence (AI) takes reusable packaging one step further. AI not only ensures companies will have the right containers in the right place at the right time but also reduces overall transportation costs, planning efforts, fuel costs and the number of required transports.
Reusable containers tend to be sturdier than single-use options, offering better protection for products during transportation as well. They reduce damage rates and product loss while improving quality and increasing the overall customer experience. This is a key factor in the growth of the global reusable packaging industry — coupled with AI’s benefits to logistics and supply chain management. For instance, the most recent Reusable Packaging Association report illustrated how the global packaging market reached approximately $950 billion in value. An estimated $200 billion of this market has been identified as transport packaging of which, 50% ($100 billion) falls under the reusable category.
Essential Building Blocks for an Efficient System
Today, automated supply chains rely on a network of reusable containers and packaging like pallets, crates, containers, and other packaging materials designed for multiple cycles. Forward thinking companies that monitor the location and status of reusable containers throughout the supply chain have improved visibility on inventory levels and can better demand forecast during peak seasons to avoid stockouts or shipment delays.
Artificial intelligence (AI) is streamlining complex logistical moves for reusable packaging. This is especially true for containers as they move throughout the country in either closed or open pooling cycle, where route determination, backhauls, and stock transfers can be optimized for cost savings while minimizing the impact on the supply chain. AI-powered systems go beyond simple inventory checks and instead forecast demand for specific containers more accurately than ever before. They even suggest optimized transport orders and streamline operations. AI can pull the data from tracking technologies (barcodes, RFID) that are needed to monitor container locations and conditions in order to further minimize losses, and ensure prompt returns and orders withing the pool.
The Complex Ecosystem of Reusable Packaging
A vast network of manufacturers, retailers, and logistics companies rely on massive pools of reusable assets. These assets, which can number in the tens of thousands or even millions, include palettes, crates, ULDs, containers, and hundreds of variations in container types. In an ideal scenario, these assets travel a complex journey, moving between suppliers, factories, warehouses, distribution centers, retail stores, and cleaning and repair facilities.
Today’s complex logistics landscape faces several challenges. Volatile markets and densely interconnected supply chains create difficulties, even though companies are collecting ever-increasing amounts of data throughout the value chain. Unfortunately, this data often remains siloed and isn’t translated into actionable insights for decision-making. This leads to discrepancies between the actual and virtual inventory of returnable assets. Additionally, fragmented software systems manage incoming and outgoing assets without real-time integration, making it difficult to identify and address misplaced or delayed containers.
The lack of transparency, combined with unplanned changes, frequent delays, and the pressure of handling time-sensitive assignments, creates a significant risk for complex operations. For example, a customer ordering excess empty containers so that they have plenty on hand can lead to an oversupply of container inventory and little space to store it. This, in turn, could leave another high-volume location scrambling to fulfill critical orders due to a container shortage at their production site.
From Data Overload to Intelligent Decisions
Even with modern tracking technologies like Auto-ID and telematics feeding data into a central platform, the sheer volume of container and transaction information can obscure certain inefficiencies. For instance, when human dispatchers struggle to maintain a complete picture of the status, location, and route for hundreds of thousands of containers throughout the supply chain cycle, many critical questions may continue to be unanswered — such as the condition of their assets, where they will be needed, and in what quantity. Planners are only human and slight demand trends in the data may be overlooked. It is important to know if the current planning for all orders factors in damaged containers and fully accounts for the cleaning process and redistribution times.
For truly optimized, demand-driven distribution, transparency is just the first step. The real power lies in making swift and intelligent decisions. This is where AI shines. AI algorithms can analyze vast amounts of data in real-time, not only recommending optimal actions but automating some of the most frequent and high-volume decisions, such as generating transport orders.
AI takes a comprehensive approach to forecasting container demand and identifying potential issues. This includes dispatcher expertise (domain knowledge), data from external systems like ERP and PPS, pre-defined stock level rules, and historical data analysis. By considering all of these factors, AI can make highly accurate forecasts and sound decisions.
Uncovering Hidden Patterns to Drive Action
A key strength of AI lies in its ability to unearth hidden insights from massive datasets.
AI can recognize patterns and connections across vast amounts of data from diverse sources. In doing so, valuable knowledge and actionable recommendations are delivered. Machine learning takes this a step further by enabling AI to learn and improve iteratively from the data itself. These algorithms can analyze entire systems from a holistic perspective, identifying previously unknown patterns without needing specific instructions.
For instance, if a customer consistently builds high safety stock levels well before actual needs, it wouldn’t be uncommon for the human dispatchers, through experience, to delay empty container orders by a few days in order to optimize overall efficiency. This kind of knowledge comes from years of learning the optimal stock level for reordering. Machine learning can replicate and enhance this process for optimal results. It can observe such patterns, link them to other data points (like predicting when the customer will need more containers), and after a training phase, automatically adjust orders to better align with actual demand and optimal transport.
Reusable Packaging and AI for a Smarter Supply Chain
While data-driven AI plays a crucial role, a truly optimized approach leverages a hybrid model that combines data with human expertise. AI techniques (e.g., constraint programming), together with OR algorithms (e.g., mathematical optimization), can explore millions of alternative decision options extremely quick to deliver truly optimized results. By considering countless options, AI can identify the optimal course of action for a given situation, either executing it autonomously or suggesting it to the planner, even in areas like AI-ads optimization for digital campaigns.
This technology makes it possible to manage complex container and reusable packaging networks with a high level of planning and service quality. It can not only send a warning to users in the event of bottlenecks, but can also ensure that the required quantities are available in the right place at the right time by automatically balancing containers in real time while keeping important metrics like transport cost and new container purchases in mind.
Expert guest authors are encouraged to share their perspectives at PackagingRevolution.net. Reach out to rick@packagingrevolution.net to find out more. (subscribe to the free newsletter).
