While generative AI has generated great excitement, a form of artificial intelligence called causal AI may offer much more potential. Causal AI offers the tantalizing promise of being able to unravel the complex web of cause and effect relationships that govern business operations. Georgia Pacific (GP) has pioneered the application of Causal AI to achieve touchless commerce.
Georgia Pacific and its subsidiaries manufacture and distribute a wide range of consumer products, including bath tissue, paper towels, napkins, tableware, paper-based packaging, cellulose, specialty fibers and building products. With an extensive network of over 150 facilities and approximately 30,000 employees, the company ranks as the second largest forest products company in the world.
A perfect command is hard to follow!
According to Georgia Pacific Vice President, Mike Carroll, “To create a more streamlined order management process, we needed a capability to navigate the complexities of the individual orders we receive every minute, hour and day. Enabled. We needed to identify near-real patterns, anomalies, and automation opportunities. More importantly, we were subject matter experts It was necessary to acquire the knowledge of how to do all this.
Achieving the perfect order is a struggle for almost every business. Orders come in, and customers expect their product to be delivered when they want it. The goal is to deliver 100% of orders on time and in full. But for that to happen, all the dominoes must fall into place: the product must be available as promised, there must be sufficient shipping capacity, and there must be an understanding that inventory between mills and distribution centers needs to be managed. How will it be transferred? To effectively address this problem, the system must also proactively identify potential bottlenecks, resource constraints, and delivery delays.
IT systems can be part of the problem. Complexities associated with the available-to-promise functionality of an enterprise resource planning system can lead to ERP system downtime, requiring time-consuming human intervention before users can make the correct promise.
The functionality available to promise seeks to ensure that the company has the required manufacturing and logistics capacity to deliver the order to the customer on the date they want it. However, complex process manufacturing presents a more difficult ATP problem than discrete industries. In GP, the same product can be manufactured using different raw materials. These different inputs lead to variable output.
According to Ron Norris, director of innovation at GP, Causal AI has been used to “detect and correct common and unusual order errors or discrepancies in near real-time. It can do this because it allows order management to Taught by subject matter experts within the team, he learned how to solve problems every hour of every day. Causal AI helps our employees in their decision-making process Empowers by acting as a valued agent to do.
A key strength of the implemented system lies in its ability to incorporate customer-centric insights into the order management process. It analyzes new and historical order data, customer preferences and transactions. This allows the system to personalize and tailor the processing of orders to each customer’s expectations.
Buy driving user
One of the challenges associated with implementing any new solution is getting users to trust and use the system. Ideally, Causal AI works autonomously. Sometimes this is not possible.
According to Mr. Carroll, when the system “can’t make an independent decision, the system will provide recommendations on how to solve the problem and then explain to the employee why it is making that recommendation. Then The employee can validate the system’s recommendation or make changes to it. It’s a different way of doing things.”
What is Causal AI?
GP defines Causal AI as a combination of Knowledge AI and Data AI. Knowledge incorporates AI domain-specific expertise and best practices provided by subject matter experts. Data AI gives systems the power to analyze large amounts of data, identify patterns and generate probabilistic results in near real-time. The combination of these two things allows Causal AI to solve very difficult problems. For example, GP’s ATP problem is not one that a supply chain planning engine can hope to solve.
The real power of Causal AI comes from understanding how knowledge and data help determine causality. Causal AI uses sophisticated causal graphs to make decisions at multiple levels. A causal model graph represents a network of interconnected entities and relationships, enabling the system to understand how different factors influence each other to produce a better outcome. By leveraging causal knowledge and data graphs, Causal AI can navigate complex business scenarios, predict outcomes, and recommend optimal courses of action.
Using words to describe Causal AI only gets you so far. It is more powerful to visualize the layers of knowledge modeled in a knowledge graph. The following figure helps demonstrate the depth of causality that has been modeled with these systems. For GP, flexibility is one of the 12 key product attributes for any of their products. The softness itself has 10 attributes called influencing properties (IA) that can affect the softness of the product. Further, each affect feature has a number of items that can affect them. BULK is one of those impressive attributes. But BULK, in turn, has many “conditional attributes” that affect it.
Causal Knowledge Graphs create deep cause and effect models.
Georgia Pacific used technology from Paraable.ai to build its Causal AI solution, and Vassar Labs built the interface. Prior to working with GP, Paraable.ai provided solutions for the financial industry.
GP has significantly improved its capabilities.
The goal of GP was to see if Causal AI could combine the refined knowledge of subject matter experts with production data to make more intelligent and automated decisions. They proved they could.
Touchless order throughput increased by 10X. Some order management errors that used to take days to resolve are now resolved in seconds. Of course, getting the promise right is crucial. However, good customer service also demands prompt responses to customer order inquiries.
The integration of Causal AI with GP’s order management system also allowed GP to engage in transportation monitoring and optimization, automated replenishment, and it aligned demand forecasts with production plans. What’s better?
Georgia Pacific decided that attacking the order management process was a good place to test the capabilities of Causal AI. Mr. Carroll emphasized, however, that “while we looked at order management first, Causal AI can be used in multiple areas of an enterprise where complexity exists.” For example, GP has had success with Causal AI in solving difficult sourcing problems.