Self-Improving Supply Chains Have Arrived
Imagine a world where supply chain planning systems can mold themselves into their environment, adapt, and improve as the business changes. Imagine systems that can monitor user behavior as well as customer and supplier anomalies, and advise accordingly. These are self-repairing supply chains.
Imagine no more. With advances in processor speed and abundance of memory, as well as recent developments in artificial intelligence (AI) techniques and ability to search for cause-and-effect relationships in large quantities of data, this luxury is upon us today.
Three areas of AI are of particular interest to supply chain planning systems:
- Machine learning and inference techniques.
- Optimization algorithms, including planning and scheduling.
- Big data and techniques to uncover hidden information.
Supply chain planning systems can greatly benefit from combining these three approaches so they become more intelligent, dynamic, and user friendly to the extent they can explain their decisions if users question the answers.
This will result in automated decision making and less reliance on subjective decisions, and much faster analysis and response to changes in the environment. It also ensures that every decision moves the organization closer to profitability, market share, or any other objectives.
AI learning systems are intended to make software more intelligent by learning from its environment as the system is exposed to more data. A company’s supply chain model can have the ability to constantly change because the supply chain itself is dynamic and the company being modeled is continuously changing.
In some cases, those changes are subtle, such as demand falling slowly over time. Other times, they are more obvious events, such as losing a customer or a supplier. Enough intelligence can be built into systems, however, so that they can learn about such behaviors and adjust themselves.
By using techniques in big data and predictive analytics, the system constantly corrects models so they represent an accurate view of what is actually occuring. Then, optimization techniques can yield a much better result of what needs to be done using the planning algorithms and heuristics.
Inventory has always been the biggest blessing and curse of every company. But now, techniques can constantly monitor not just what has been used but also what is expected to be used. Based on that, the system can recommend the best levels of inventory for every part number at every level of the supply chain.
Learning from past usage leads the system to the needs of the future with a certain degree of confidence. Based on this, the system makes decisions to ensure on-time delivery at the lowest possible cost.
Users can also train the systems to compare progress against management’s set goals. They do this by predicting what is expected on the supply side, and comparing it with the goals. When deviations fall outside acceptable limits, the system can and will decide on changes to the plan to bring about a more favorable solution.
Industry has reached an inflexion point—moving from an information age to a decision automation age. As this trend continues, human beings need only specify their objectives, and systems will offer feasible solutions and relevant costs.
But in order to do so, these systems need to have a realistic understanding of the world around them to know all the options.